Wiki Log — 2026Q3
2026-09-11(newsletter run,web 源)
- 处理 2 份 newsletter(跳过 gmail 源,应 Jean 要求):
raw/newsletters/Every/2026-09-11 Evals for Everyone.md→ 更新claude-code/self-improving-skills(个人基准把 eval loop 从单技能扩展到全部工作;Luna 在个人任务上逆袭 Fable/Sol;主观品味可二值化评测,收窄 open question)raw/newsletters/Ben's Bites/2026-09-11 Telling AI to design is hard.md→ 更新harness-engineering/factory-missions-architecture(Ben's session #6 Droid 实战案例:开源执行 + 旗舰编排 + computer-use 验证、20 并发 subagent、design.md 清上下文仪式、381M token 账单)
- 无新页面创建,无 candidate 晋升;两页均保持
knowledge_status: ai_draft,待 Jean review。
[2026-09-01] wiki-daily-update | 1 file discovered, 0 new absorptions
Files discovered
raw/briefing/AI Briefing/2026-08-31-23-04.md→ already absorbed (hash match; previously touched 6 wiki pages on 2026-08-31)
Files absorbed
- None (all discovered files matched previous absorb log)
Files committed from previous run
- 1 raw file added
- 6 wiki pages updated by the 2026-08-31 evening briefing
wiki/index.mdandwiki/_backlinks.jsonrebuilt
Optional raw emergence
- Skipped (only 1 file discovered, below 5-file threshold)
Index & embeddings
qmd update && qmd embed: 5 new, 30 updated, 1929 unchanged, 0 removed; embedded 289 chunks from 35 documents in 10s
Prompts for witness
- Generated 6 prompts across 6 mature pages
- Saved to Prompts for Witness — 2026-09-01
Commit
wiki-daily-update 2026-09-01 - 12 files changed
[2026-08-31] wiki-daily-update | 4 files discovered, 0 new absorptions
Files discovered
raw/briefing/AI Briefing/2026-08-30-08-10.md→ already absorbed (hash match)raw/briefing/AI Briefing/2026-08-30-17-41.md→ already absorbed (hash match)raw/briefing/AI Briefing/2026-08-30-23-07.md→ already absorbed (hash match)raw/briefing/AI Builders Digest/2026-08-30.md→ skipped_duplicate (merged into 2026-08-30-17-41 absorb)
Files absorbed
- None (all discovered files matched previous absorb log)
Wiki pages touched
- None in this run
Optional raw emergence
- Skipped (only 4 files discovered, below 5-file threshold)
Index & embeddings
- Rebuilt
wiki/index.md(452 pages) andwiki/_backlinks.json(1083 targets) qmd update && qmd embed: 24 new, 46 updated, 1889 unchanged, 0 removed; embedded 695 chunks from 70 documents in 22s
Prompts for witness
- Skipped (no new absorptions today)
Commit
wiki-daily-update 2026-08-31 - 0 files changed
[2026-08-30] wiki-emerge | last 14 days | 107 sources scanned
Range
- 2026-08-16 to 2026-08-30
Output
Top themes
- Agent maintenance burden / personal vs shared agent scaling
- Harness as differentiator (Flue, Headway Eddy, Agent SDK)
- Parameterized AI cost governance (circuit breaker, usage visibility, task routing)
- Security boundary shift from sandbox to fences/rules + credential isolation
- Private / internal eval replacing public benchmarks (CentaurBench, Thinkingbox, KateBench)
- Mobile / cross-channel / voice agent as new interface surface
- AI writing quality & detection tension (Deft, Claude watermark, AI slop)
- AI adoption levels & org design (Every 8-level model, Thesis Statements)
- Local/open-source catch-up and hybrid model architecture
Pending Jean review
- Promote "Agent Maintenance Tax" to concept?
- Update claude-code/overview (adoption levels, personal agent maintenance, remote/mobile, Agent SDK boundary)
- Update harness-engineering/overview (cost optimization, security boundaries, eval engineering, login agency, multi-agent orchestration)
- Update product-trends/overview (metered intelligence, mobile/voice interfaces, hybrid architecture, AI writing/data business)
- Build personal parameterized AI budget / circuit breaker for OpenClaw
- Start private eval suite for high-frequency workflows
- Draft personal Agent safety playbook based on Hugging Face / Headway / Yegge fences
Commit
- Only
outputs/ideas/2026-08-30-raw-emergent-themes.mdand this log entry changed.
[2026-08-28] wiki-absorb | 2 files absorbed, 10 wiki pages touched
Files absorbed
raw/newsletters/Ben's Bites/2026-08-28 Who let the agents in.md→ absorbed (new)raw/newsletters/Every/2026-08-28 Our ChatGPT and OpenClaw Guides Just Got an Overhaul.md→ absorbed (new)
Wiki pages touched
product-trends/agent-native-architecture— added ChatGPT Work credential-isolated login sectionharness-engineering/agent-memory-vs-context-substrate— added Claude cross-device unified memory sectionai-ecosystem/ai-chip-architecture— promoted candidate→mature, added Jalapeño full-stack co-design case studyharness-engineering/agent-trust-verification— added OpenAI Hugging Face loss-of-control incident sectionharness-engineering/realtime-voice-agent-systems— added Gemini 3.5 Transcribe evidenceai-ecosystem/overview— added infrastructure-race framing from Everyclaude-code/personal-agent-minimal-setup— promoted candidate→mature, added maintenance burden sectionharness-engineering/copilot-vs-delegate— added Delegate vs Collaborate and /goal sectionharness-engineering/overview— added Every infrastructure/harness insightsclaude-code/overview— added Every Chat/Work/Codex and maintenance insights
Index & backlinks
- Rebuilt
wiki/index.mdandwiki/_backlinks.json
Pending Jean review
- All touched pages remain
knowledge_status: ai_draft ai-chip-architectureandpersonal-agent-minimal-setupwere promoted from candidate to mature; worth a quick review
[2026-08-28] wiki-daily-update | 1 file discovered, 0 new absorptions
Files discovered
raw/briefing/AI Briefing/2026-08-27-08-49.md→ already absorbed (hash match; previously touched 10 wiki pages on 2026-08-27)
Files absorbed
- None
Wiki pages touched
- None in this run
Index & embeddings
- No wiki index changes required
qmd update && qmd embed: 4 new, 13 updated, 1918 unchanged, 0 removed; embedded 224 chunks from 17 documents in 8s
Prompts for witness
- Skipped (no new absorptions today)
Commit
- No wiki changes to commit
[2026-08-27] wiki-daily-update | 5 files discovered, 0 new absorptions
Files discovered
raw/briefing/AI Briefing/2026-08-26-08-39.md→ already absorbed (hash match)raw/briefing/AI Briefing/2026-08-26-18-48.md→ already absorbed (hash match)raw/briefing/AI Briefing/2026-08-26-23-36.md→ already absorbed (hash match)raw/briefing/AI Builders Digest/2026-08-26.md→ missing from_absorb_log.json, but content already reflected in ai-ecosystem/agent-first-search; logged idempotencyraw/newsletters/Every/2026-08-27 Benchmarks Don't Know Your Job.md→ already absorbed (hash match)
Files absorbed
- None (all 5 discovered files were already processed; Builder Digest log entry backfilled)
Wiki pages touched
- None in this run (agent-first-search was already created in the 2026-08-26 afternoon absorb run)
Index & embeddings
- Rebuilt
wiki/index.md(449 pages) andwiki/_backlinks.json(1224 targets) qmd update && qmd embed: 22 new, 41 updated, 1868 unchanged, 1 removed; embedded 615 chunks from 62 documents
Prompts for witness
- Generated 6 prompts across 6 pages → Prompts for Witness — 2026-08-27
Commit
wiki-daily-update 2026-08-27 - 14 files changed
Pages touched: ai-ecosystem/overview, harness-engineering/overview, harness-engineering/model-routing, claude-code/overview Key additions: 更新 ai-ecosystem/overview(Ox Alpha = GLM-5.3-Flash、OpenWorker 本地安全 agent);更新 harness-engineering/overview(OpenWorker 可审计本地安全 harness、模型留存率作为真实 benchmark);更新 harness-engineering/model-routing(留存率指标、GLM-5.3-Flash 路由数据点);更新 claude-code/overview(AGENTS.md/CLAUDE.md 分裂与 Anthropic 回应、AI 原生开发流程、Cursor Thermo-Nuclear skill)。 Files processed:
- AI Briefing 2026-08-26 Evening → absorbed, then regenerated with AI-relevance filter for timeline sections (sha256:4b493c69...)
[2026-08-26] absorb | AI Briefing 2026-08-26 Afternoon
Pages touched: ai-ecosystem/agent-first-search, ai-ecosystem/overview, harness-engineering/model-routing, claude-code/overview Key additions: 创建 candidate concept Agent-First Search(Parag Agrawal / Parallel Web Systems 的 agent-first 搜索基础设施与 Shapley value 内容归因);更新 ai-ecosystem/overview(OpenAI 自研芯片、ChatGPT/Codex Team 计划、Parallel Web Systems);更新 harness-engineering/model-routing(Databricks smart router 30%+ 成本降低、50%+ benchmark 节省);更新 claude-code/overview(Claude Chat/Cowork 统一记忆上线)。 Files processed:
- AI Briefing 2026-08-26 Afternoon → absorbed (sha256:ffcef98b...)
[2026-08-26] wiki-daily-update | Ben's Bites — Agents on your mobile
Pages touched: product-trends/mobile-agent-boundary, claude-code/overview, ai-tools/overview, product-trends/overview, ai-ecosystem/overview Key additions: 创建 candidate concept 移动 Agent 使用边界;更新 claude-code/overview(Claude Academy 教育理念、手机远程控制);更新 ai-tools/overview(Skydive 常驻 cloud agent);更新 product-trends/overview(debloat.dev 反臃肿开源替代);更新 ai-ecosystem/overview(Etna Labs 数据生意"流 vs 存量"框架)。 Files processed:
- Ben's Bites — Agents on your mobile → absorbed (sha256:0c2d7d96...)
- 顺带 commit 了 2026-08-25 晚间未提交的 Every 文件与 AI Briefing raw 文件。
[2026-08-25] absorb | AI Briefing 2026-08-25 Evening + AI Builders Digest 2026-08-25
Pages touched: claude-code/overview, ai-ecosystem/overview, harness-engineering/overview, product-trends/overview Key additions: Claude Code ↔ Codex 官方 handoff 插件 codex-plugin-cc;GPT-5.6 /goal 下的过度防御行为;Codex 一句话配置新电脑;前沿模型 Specialist 格局(Opus 5 / GPT-5.6 / Kimi K3 / GLM-5.2 各有专长);OpenAI DevDay 2026 与 Plus 5 小时限额回归;Kimi K3 跨学科概念设计;eval 的 discriminatory property;Dan Koe 未来三种人;Peter Yang 的 AI chiefs of staff 与语音客服;Replit Agent 替代 Claude CoWork;Aaron Levie systems of record / ZDR;v0.com 反 bloated 轨迹。 Files processed:
- AI Briefing 2026-08-25 Evening → absorbed (sha256:a13e3e8a...)
- AI Builders Digest 2026-08-25 → absorbed (sha256:ad8bd9ce...)
[2026-08-25] absorb | AI Briefing 2026-08-25 Afternoon (regenerated)
Pages touched: claude-code/overview, ai-ecosystem/overview, harness-engineering/overview Key additions: 同一会话切换模型会清空 prompt cache(Teknium);Cursor Thermo-Nuclear Code Quality Review skill 的结构简化实践;ScarletKc_ Codex review skill 的用户可见文本规范;Matthew Berman 对 Tibo 访谈中 ChatGPT/Codex 融合、personal AGI、cloud agent、递归自我改进;Codex 额度滥用导致「跑完任务」福利取消;Pi/Maka harness 架构趋同;coding vs engineering 的能力边界;mattpocockuk 的 skill 调用最佳措辞;Claude Code 2.1.245 发布。 Files processed:
- AI Briefing 2026-08-25 Afternoon → regenerated and re-absorbed (sha256:73971367...)
[2026-08-25] absorb | AI Briefing 2026-08-25 Morning
Pages touched: claude-code/overview, harness-engineering/long-running-agent-harness, ai-ecosystem/overview, product-trends/overview Key additions: Claude web/desktop 流式渲染优化 4 倍;Opus 5 争议与用户反馈;fx 开放协议与 Unix 哲学;AI agent red flags 清单;Pi/Maka harness 架构趋同进一步确认;Mastra Observational Memory 96% 缓存命中;ox alpha 潜状态递归更新 LLM;OpenAI × AWS 优化 Kiro/GPT-5.6;推理经济学灰色市场;Omarchy agent-first Linux 桌面;AI 交互三范式;malleable software 与个人软件崛起。 Files processed:
- AI Briefing 2026-08-25 Morning → updates to 4 overview/concept pages
[2026-08-24] absorb | AI Briefing 2026-08-24 Afternoon
Pages touched: claude-code/overview, harness-engineering/long-running-agent-harness, ai-ecosystem/overview, product-trends/overview Key additions: Codex 额度滥用事件与政策收紧;Codex + OCR 操控手机微信自动回复;Pi/Maka runtime 架构趋同;DeepSeek Harness 98.2% 缓存命中;Alma prune+spill 互证;OpenRouter "智能便宜 100 倍"对谈;小米 AI 本地主机;Ox Alpha 视觉-代码还原;ChatGPT Work 争取 Uber Cash 补偿;康威定律与 AI 外科手术团队;Omarchy agent-first Linux 桌面。 Files processed:
- AI Briefing 2026-08-24 Afternoon → updates to 4 overview/concept pages
[2026-08-24] wiki-daily-update | 2026-08-24 complete — 4 files absorbed, 157 queued, emergence run
Files discovered
raw/briefing/AI Briefing/2026-08-20-08-33.md→ absorbedraw/briefing/AI Briefing/2026-08-23-02-15.md→ absorbedraw/newsletters/Ben's Bites/2026-08-23 How I built this.md→ absorbedraw/newsletters/Every/2026-08-23 The Healthcare Company That Built the AI Tool It Couldn't Buy.md→ absorbed- 157 previously classified
idea_candidatefiles remain pending for emergence
Files absorbed
- AI Briefing 2026-08-20 morning: GLM-5.3 post-training scaling, Hermes Agent, Learn Harness Engineering, Claude Managed Agents updates, team skill GitHub plugin distribution
- AI Briefing 2026-08-23 evening: Pi 50h harness reflection, serverless long-running execution, model-harness coupling, Codex CLI 25x speedup, ThreeUI, matt skills /implement-spec workflow, AI tool build-vs-buy ROI boundary
- Ben's Bites 2026-08-23: Ben Tossell personal agent minimal file practice, manual memory strategy, agent agreeableness trap, git-over-log.md
- Every 2026-08-23: Headway Eddy case, Docker container isolation, read-only data, restricted network, no-outbound compliance harness design, Wait/Buy/Build decision framework, HTML artifact as internal shareable output, viral AI adoption via excellent outputs
Wiki pages touched
- ai-ecosystem/hermes-agent
- ai-ecosystem/zhipu-glm5-scaling-pain
- harness-engineering/walkinglabs-learn-harness-engineering
- claude-code/skills-collection
- claude-code/overview
- ai-ecosystem/overview
- harness-engineering/overview
- harness-engineering/model-harness-fit
- harness-engineering/long-running-agent-harness
- product-trends/overview
- claude-code/personal-agent-minimal-setup (new candidate)
- product-trends/ai-tool-build-vs-buy-decision (new candidate)
Index & embeddings
- Rebuilt
wiki/index.md(447 pages, 13 sections) andwiki/_backlinks.json(1040 targets) - Smoke check passed: claude-code/overview, harness-engineering/overview, product-trends/overview present
Raw emergence
- 90 pending idea_candidate files from last 14 days + 4 newly absorbed files clustered
- Report: 2026-08-24 Raw Emergent Themes
- Key themes: personal agent minimal setup, harness-memory coupling, enterprise build-vs-buy, model launch one-offs, skill-as-workflow, long-running execution
Prompts for witness
- Generated 6 prompts across 4 themes → Prompts for Witness — 2026-08-24
Commit
wiki-daily-update 2026-08-24 - 5 files changed
[2026-08-23] absorb | AI Briefing 2026-08-23 Evening
Pages touched: harness-engineering/model-harness-fit, harness-engineering/long-running-agent-harness, claude-code/overview, harness-engineering/overview, ai-ecosystem/overview, product-trends/overview, product-trends/ai-tool-build-vs-buy-decision Key additions: Pi 50h harness 反思(prune+spill、Lane、数据库事务、崩溃恢复);serverless 长程执行与多 worker 设计;model-harness 耦合深化(harness 专用参数幻觉);Codex CLI 25x 启动速度;ThreeUI 开源;matt skills 与 /implement-spec 工作流;AI 工具化 ROI 边界(洗碗机类比)。 Files processed:
- AI Briefing 2026-08-23 Evening → harness-engineering/model-harness-fit, harness-engineering/long-running-agent-harness, claude-code/overview, harness-engineering/overview, ai-ecosystem/overview, product-trends/overview, product-trends/ai-tool-build-vs-buy-decision
[2026-08-23] absorb | Ben's Bites — How I Built This
Pages touched: claude-code/overview, harness-engineering/overview, claude-code/personal-agent-minimal-setup Key additions: Ben Tossell 个人 agent 最小文件实践(AGENTS.md / code.md / todos.md / memory.md);手动维护 memory 避免自动记忆污染;agent agreeableness 作为设计陷阱;用 git 替代 log.md。 Files processed:
- 2026-08-23 How I Built This → claude-code/overview, harness-engineering/overview, claude-code/personal-agent-minimal-setup
[2026-08-23] absorb | Every — The Healthcare Company That Built the AI Tool It Couldn't Buy
Pages touched: harness-engineering/overview, claude-code/overview, product-trends/overview, product-trends/ai-tool-build-vs-buy-decision Key additions: Headway 基于 Claude Code SDK 自研 Eddy(650/900 员工每日使用,26 万次对话);Docker 容器隔离、只读数据、网络受限、禁止外发的合规 harness 设计;Wait/Buy/Build 决策框架成为 candidate concept;HTML artifact 作为内部可分享输出格式;AI adoption 病毒式传播需要可验证的优秀输出。 Files processed:
- 2026-08-23 The Healthcare Company That Built the AI Tool It Couldn't Buy → harness-engineering/overview, claude-code/overview, product-trends/overview, product-trends/ai-tool-build-vs-buy-decision
[2026-08-20] absorb | Every — What Does Human Work Look Like After Automation?
Pages touched: product-trends/after-automation-productivity-paradox, product-trends/human-agent-interaction Key additions: Tracked Every's Thesis Statements 2027 launch and its six practitioner claims as a testable-prediction signal for the after-automation paradox; linked Karri Saarinen's "AI's biggest problem will be design" thesis back to human-agent interaction design. Files processed:
- Every — What Does Human Work Look Like After Automation? → product-trends/after-automation-productivity-paradox, product-trends/human-agent-interaction
[2026-08-19] wiki-daily-update | No new raw files in the last 24h
Files discovered
raw/briefing/AI Briefing/2026-08-18-20-25.md— already absorbed (hash match)raw/briefing/AI Builders Digest/2026-08-18.md— already absorbed (skipped_duplicate, hash match)raw/newsletters/AINews/2026-08-15 React for Agents Astro Creator Brings Hooks to his Meta-Harness Flue.md— already absorbed (hash match)raw/newsletters/AINews/2026-08-18 [AINews] Stripe buys OpenRouter for $7B.md— already absorbed (hash match)raw/newsletters/Ben's Bites/2026-08-18 Do you use a personal agent?.md— already absorbed (hash match)raw/newsletters/Every/2026-08-16 The Next Era of Great Work.md— already absorbed (hash match)raw/newsletters/Every/2026-08-17 Our AI Costs Jumped 230 Percent I’m Not Setting Token Budgets Yet.md— already absorbed (hash match)
Files absorbed
- None (all 7 discovered files were already processed)
QMD refresh
qmd update && qmd embedexecuted- Indexed: 14 new, 27 updated, 1790 unchanged, 23 removed
- Embedded: 506 chunks from 41 documents
Prompts for witness
- None generated (no new pages or raw absorptions in this run)
Backlinks and index
- Rebuilt
wiki/index.md(443 pages) - Rebuilt
wiki/_backlinks.json(940 targets) - Smoke check passed:
claude-code/overview,harness-engineering/overview,product-trends/overviewpresent
[2026-08-19] wiki-daily-update | 2026-08-19 complete — 98 files, 4 briefings absorbed
Files discovered
raw/briefing/AI Briefing/2026-08-19-08-03.md— absorbedraw/briefing/AI Briefing/2026-08-19-18-47.md— absorbedraw/briefing/AI Briefing/2026-08-19-23-35.md— absorbedraw/briefing/AI Builders Digest/2026-08-19.md— absorbedraw/newsletters/Every/2026-08-19 What Does Human Work Look Like After Automation.md— raw only / kept for emergence
Files absorbed
All 4 Aug 19 briefings; themes merged into existing mature pages (no new candidate pages created).
Wiki pages touched
- harness-engineering/agent-trust-verification — agent containment, environmental boundaries, destructive-action fixes
- claude-code/overview — artifacts, 9 settings, session fork, desktop startup, Gmail/Drive connectors, Cowork surfaces, managed agents
- product-trends/saas-vs-agent-native — headless SaaS, agent-facing APIs, workflow ownership
- product-trends/agent-native-architecture — Cumora human-agent group chat
- harness-engineering/overview — eval as quality frontier, evals-skills plugin, continuous learning, session fork orchestration
- ai-ecosystem/overview — OpenAI RL pause, GLM-5.3 post-training scaling, Rich Sutton continuous learning, Jason Wei parametric knowledge vs tools
- ai-tools/overview — evals-skills plugin, Cumora, Pilot Harness
Index & embeddings
- Rebuilt
wiki/index.mdandwiki/_backlinks.json qmd update && qmd embed: 68 new, 31 updated, 1800 unchanged; embedded 2427 chunks from 99 documents
Prompts for witness
- Generated 10 prompts across 5 themes → Prompts for Witness — 2026-08-19
Commit
wiki-daily-update 2026-08-19 - 98 files changed(1b1a33f)
[2026-08-19] absorb | 跨国串门儿计划 2026-06-15 至 2026-08-18 AI 专题
Pages touched: ai-ecosystem/llm-inference-mechanics, ai-ecosystem/overview, harness-engineering/components-coding-agent, harness-engineering/judgment-engineering, harness-engineering/overview, product-trends/org-design-ai-age, product-trends/overview, product-trends/saas-vs-agent-native Key additions: 58 期逐字稿按五个主题聚合,更新 Agent 可靠性栈、判断工程、推理机制、应用护城河和 AI 组织设计;未创建新的节目型 wiki 页面。 Checkpoints: 15 / 30 / 45 / 60;每个检查点均复核是否需要新概念页,结论为优先更新既有父页面。 Quality boundary: 节目为 AI 翻译与声纹克隆的二手呈现;口述数字、性能、融资、政策与人物原话未升级为已核实事实。 Sources processed:
- raw/to-learn/跨国串门儿计划/episodes/2026-06-15 EP585.产品人如何烧掉简历,在 AI 时代打造真正有野心的消费产品.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-18 EP590.走进 Anthropic CEO 达里奥·阿莫代的思想世界.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-19 EP591.Matt Pocock:开发者如何用 AI 放大十倍产出,模型狂热时代的软件基本功.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-19 EP592.陈立武:66 岁接手 Intel,AI 算力战争下的半导体供应链重建.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-23 EP594.Fiona Fung:AI 时代工程师如何不掉队,代码不再稀缺后的团队重构.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-24 EP595. Lambda CTO:GPU 神话破灭后,AI 时代最稀缺的到底是什么.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-24 EP596.AI 智能体:当百万个代理开始替你谈判、花钱与协作.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-26 EP599.Nebius创始人:AI基础设施不是泡沫,但世界过度集中才是最大威胁.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-26 EP600.DeepMind预训练负责人:如何用“研究品味”敲开顶尖实验室大门.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-28 EP603.Cloudflare CEO:当机器人流量超过人类,互联网的商业模式将彻底崩塌.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-29 EP604.OpenAI Noam Brown:模型评估方式,正在错过 AI 真正的能力上限.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-29 EP605.Dwarkesh:AI 训练的下一个范式,为什么你的模型永远毕不了业.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-30 EP606.Codex 负责人:品味与判断力为何成为你最值钱的资产.md
- raw/to-learn/跨国串门儿计划/episodes/2026-06-30 EP607.SemiAnalysis创始人:AI的真正100倍杠杆,藏在软硬件协同设计里.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-01 EP608.3Blue1Brown创始人:AI攻克数学前沿,人类创造力与科学发现将何去何从.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-01 EP609.挑战英伟达:Etched AI推理芯片如何让token成本暴跌.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-02 EP612.Kent Beck:AI 时代,软件工程里“人的部分”为何比代码更难.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-04 EP614.NVIDIA 核心科学家 Bryan Catanzaro:当算力堆到极限,开源模型如何靠“效率”继续变强.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-04 EP615. Anthropic 联合创始人 Jack Clark:AI 正在让公司内部发生“相变”,你的工作还安全吗?.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-04 EP616.Matt Pocock:用一份检查清单,终结 AI Agent 的“技能地狱”.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-07 EP617.Groq创始人:从濒临破产到200亿美元NVIDIA交易,AI时代如何用提问取代回答.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-07 EP618.OpenCode 创始人:AI 编程狂潮下,如何保持清醒并找到你的不对称优势.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-08 EP619.为何我们并未处于 AI 资本支出泡沫中 - 能源主权与电力未来.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-09 EP620.Modal CTO:你的 AI 应用不该跑在K8s 上,Agent 时代的云应该长什么样.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-09 EP621.纳瓦尔:驾驭 AGI、AI 焦虑,以及加州帝国.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-10 EP622.为什么现在是应用层的最佳时机.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-11 EP623.Dylan Patel 谈驱动 AI 革命的基础设施.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-14 EP628. AI蜜月期结束:生产力提升,但质量与判断力在退化.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-17 EP630.人工智能的未来:与哈萨比斯爵士和温迪·霍尔女爵士对话.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-17 EP631.深入理解 Context engineering.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-17 EP633.图灵奖得主:GPU 与 TPU、计算机体系结构、RISC 与 CISV.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-19 EP636.Netflix 为何在 AI 时代押注系统思考者,而非专才.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-20 EP638.Agent Loop 大辩论:Loop究竟是炒作还是真有用.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-23 EP641. Sam Blond 谈人工智能原生世界中的销售未来.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-23 EP642.Kun Chen:顶尖工程师如何把 AI Agent 用到极致.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-24 EP643. 内核、强化学习与智能体奖励黑客专题.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-24 EP645.埃隆·马斯克:10年内钱将不再重要,AI时代的富足与颠簸之路.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-25 EP646.Cerebras CEO:CUDA绝非护城河.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-26 EP648.黄仁勋谈 AI 末日论者、就业担忧与中国开源模型.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-27 EP649. Anthropic 技术产品经理:为什么最优秀的产品领导者正在为 2028 年布局.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-29 EP651.OpenAI产品工程负责人:工作的未来、AI 通才、创意与品味.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-29 EP652.黄仁勋:打造英伟达的思维模式.md
- raw/to-learn/跨国串门儿计划/episodes/2026-07-30 EP653.Sam Altman 谈通用人工智能、算力与人类自主权.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-01 EP656.All-in-芯片股暴跌,200 亿美元基金遭追加保证金,前沿实验室:请放慢 AI 发展步伐.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-02 EP657.AWS 老兵:新的软件开发生命周期.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-02 EP658.Kimi杨植麟的博导预测 AI Agent的未来:为什么真正的护城河是数据、工程和基础设施.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-02 EP659.xAI 联合创始人:Igor Babuschkin 解读模型开发的未来.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-04 EP662.:谷歌首席科学家Jeff Dean- 人工智能构建中的 1%法则.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-04 EP663.Gavin Baker- AI 抛售与数据不符 - 顶级 AI 投资者解析.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-10 EP666.All-In-谷歌人才流失,SpaceX 的强劲季度,Airtable 暴跌 90%,美国数据助推中国 AI.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-10 EP667.李飞飞:利用人工智能提升你的智力与丰富人性.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-11 EP668.AI领域的下一个百倍增长:推理、网络与自我优化模型.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-11 EP669.如何构建自主、长时程 AI 智能体.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-12 EP671.Ryan Greenblatt:我们能控制 AI 递归自我改进吗?.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-14 EP675.斯坦福2026 年春季 AI 经济学课程:从 GPU 到生命科学,一次听懂 AI 超级周期的九层经济学.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-15 EP676.Ray Dalio:AI周期与未来的可能.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-15 EP677.Post-Traning 前沿现状与问题.md
- raw/to-learn/跨国串门儿计划/episodes/2026-08-17 EP678.All-In 激辩AI新格局:2万亿美元IPO、扎克伯格AI宣言、英伟达5000亿算力融资.md
- raw/to-learn/跨国串门儿计划/2026-06-15 至 2026-08-18 AI 节目专题索引.md
- raw/to-learn/跨国串门儿计划/筛选清单(2026-06-15 至 2026-08-18).md
[2026-08-19] absorb | Recent raw files (Aug 15–18)
Pages touched: harness-engineering/ai-cost-governance, harness-engineering/model-routing, harness-engineering/overview, harness-engineering/what-is-agent-harness, harness-engineering/agent-trust-verification, ai-ecosystem/overview, claude-code/overview, product-trends/environment-context-agents, product-trends/cursor-3-agent-orchestration Key additions: Created AI Cost Governance concept from Every's 230% cost spike case; updated model routing and ecosystem overview with Stripe-OpenRouter; added Flue 2 / React-for-Agents pattern to harness overview. Files processed:
- AINews — React for Agents → harness-engineering/what-is-agent-harness, harness-engineering/overview
- Every — The Next Era of Great Work → harness-engineering/agent-trust-verification
- Every — AI Costs Jumped 230 Percent → harness-engineering/ai-cost-governance
- AI Builders Digest 2026-08-18 → ai-ecosystem/overview, harness-engineering/overview
- AI Briefing 2026-08-18 Evening → claude-code/overview, harness-engineering/overview
- [[raw/newsletters/AINews/2026-08-18 [AINews] Stripe buys OpenRouter for $7B.md|AINews — Stripe buys OpenRouter]] → harness-engineering/model-routing, ai-ecosystem/overview
- Ben's Bites — Do you use a personal agent? → product-trends/environment-context-agents, ai-ecosystem/overview
[2026-08-19] absorb | AI Briefing 2026-08-19 Morning
Pages touched: claude-code/overview, harness-engineering/overview, ai-ecosystem/overview, product-trends/overview Key additions: Agent-as-code/harvester-tuner citizen-dev pattern; destructive operation guardrails for coding agents; eval skills plugin; human-agent group chat (Cumora); tool use vs parameterized knowledge debate; OpenAI frontier RL pause for safety; headless SaaS for agents; AI-era design observations from Ian Silber. Files processed:
- AI Briefing 2026-08-19 Morning → claude-code/overview, harness-engineering/overview, ai-ecosystem/overview, product-trends/overview
[2026-08-19] absorb | AI Briefing 2026-08-19 Evening
Pages touched: ai-ecosystem/overview, claude-code/overview, ai-tools/overview Key additions: Post-training scaling as independent dial (GLM-5.3); skill audit methodology (description as trigger, unslop standard, blast radius verification); Blume cross-harness search tool. Files processed:
[2026-08-18] absorb | The Next Era of Great Work
Pages touched: Agent Trust Verification Key additions: Verification now covers negative paths, authorization boundaries, independent review, and always-on Agent controls, with paywalled method details kept unverified. Classification: reusable concept evidence; the newsletter issue remains in raw. Files processed:
- Every - The Next Era of Great Work -> Agent Trust Verification Decision: absorbed / absorb_now; hash: sha256:36d314874c944fc67322aa685c6ba7de5cf6f6b08bc32a6019d4605bbdd34366
[2026-08-18] absorb | React for Agents: Flue 2
Pages touched: What is an Agent Harness? Key additions: Flue 2 provides evidence for treating Hooks as a runtime composition layer that can change an Agent's capability boundary with context; adoption, performance, and production evidence were not supplied. Classification: reusable concept evidence; the newsletter issue remains in raw. Files processed:
- AINews - React for Agents: Flue 2 -> What is an Agent Harness? Decision: absorbed / absorb_now; hash: sha256:989f7cb2e295bc28774926c42432c13e1d0b9e8881a51d0fdba5fadd7c81e155
[2026-08-18] absorb | Our AI Costs Jumped 230 Percent
Pages touched: Token Optimization Economics Key additions: Every's Sol incident adds an evidence-driven operating loop of circuit breakers, visible spend, cost-output-learning review, and adjustable friction instead of a fixed token policy. Classification: reusable concept evidence; the newsletter issue remains in raw. Files processed:
- Every - Our AI Costs Jumped 230 Percent -> Token Optimization Economics Decision: absorbed / absorb_now; hash: sha256:7b90c2897970e8190f97d91596e520ca800809ff3ac1df24038c47c83a06f6ec
Pending Jean review
- What is an Agent Harness? -
ai_draft; suggested action: verify whether Flue 2's Hooks design is reusable beyond this single source, or downgrade to raw/source material. - Agent Trust Verification -
ai_draft; suggested action: verify the negative-path and always-on-agent security synthesis, or mark as hypothesis/disputed. - Token Optimization Economics -
ai_draft; suggested action: verify whether evidence-driven budget parameters should become a durable operating principle, or downgrade to raw/source material.
[2026-08-18] absorb | Ben's Bites 2026-08-18 — Do you use a personal agent?
Pages touched: product-trends/environment-context-agents Key additions: Detailed ChatGPT Computer History mechanism, privacy controls, and prompt-injection risks from Ben's Bites. Files processed:
[2026-08-18] absorb | AINews 2026-08-18 — Stripe buys OpenRouter for $7B
Pages touched: ai-ecosystem/qwen-36-agent-leap, harness-engineering/multi-agent-coordination-patterns, product-trends/cursor-3-agent-orchestration, ai-ecosystem/model-labs-becoming-agent-labs Key additions: Qwen3.8-27B reaches frontier Intelligence Index; multi-agent operationalization; Cursor Origin code-hosting; Stripe–OpenRouter validates routing-layer value. Files processed:
- [[raw/newsletters/AINews/2026-08-18 [AINews] Stripe buys OpenRouter for $7B.md|AINews 2026-08-18]] → ai-ecosystem/qwen-36-agent-leap, harness-engineering/multi-agent-coordination-patterns, product-trends/cursor-3-agent-orchestration, ai-ecosystem/model-labs-becoming-agent-labs
[2026-08-18] absorb | AI Briefing afternoon + backlog classification
Files processed: 110 candidates from the last-30-day mtime scan; 1 absorbed, 1 skipped_duplicate, 18 skipped_one_off, 90 idea_candidate.
Pages touched: claude-code/overview, claude-code/claude-design, harness-engineering/self-verification-loops, product-trends/token-optimization-economics, Wiki Index, Backlinks Index
Key additions: /design research preview and the agent workspace harness checklist were added to Claude Code pages; candidate sampling plus trace-based evals were added to self-verification; return on invested tokens and workflow-first cost optimization were added to token optimization economics.
Files processed:
- AI 简报 2026-08-18 Afternoon → four existing wiki pages
- AI Builders Digest 2026-08-18 → skipped_duplicate because it is merged into the briefing
- 90 historical newsletter backfill files → idea_candidate / emerge_later; deferred to cross-source emergence
- 18 historical or test briefing files → skipped_one_off / raw_only
Pending Jean review
- claude-code/overview —
ai_draft; suggested action: keep draft / verify/designbehavior / downgrade the product update to source material. - claude-code/claude-design —
ai_draftinherited from the page; suggested action: verify research-preview scope and test the handoff. - harness-engineering/self-verification-loops —
ai_draft; suggested action: keep method, independently verify the reported benchmark and cost numbers. - product-trends/token-optimization-economics — existing AI-drafted synthesis; suggested action: verify the podcast claims before treating them as enterprise evidence.
- 90 newsletter files —
idea_candidate; suggested action: run raw emergence after the backfill window is stable.
[2026-08-15] wiki-daily-update | 2 files skipped (duplicate/stale)
Files processed:
- AI Builders Digest 2026-08-14 → skipped_duplicate(Kevin Scott agentic web / Claude Code postmortem / Managed Agents 已通过其他源吸收)
- AINews 2026-07-02 → skipped_one_off(两月前 stale newsletter,内容已覆盖)
[2026-08-14] wiki-daily-update | 2 files reconciled + 1 new candidate
Files processed: 2 Pages touched: agent-complexity-less-is-more(新建 candidate), dreamer-platform-personal-agent(关联链接), Wiki Index, Backlinks Index Key additions: 补齐 Ben's Bites / Every 2026-08-13 两个文件在 absorb log 的记录(此前 wiki 页已写入但 log 未登记);新建概念页「Agent Complexity — Less Is More」(Ben 对 Grok Bot 的「less is more」判断,candidate/ai_draft,1 source);重建 index(441 页)与 backlinks。 Decisions: 2×absorbed(absorb_now);语音礼仪与内容水印溯源仍作 idea_candidate 待跨源涌现。 Files processed:
- Ben's Bites 2026-08-13 → agent-complexity-less-is-more + grok-4-6
- Every 2026-08-13 → ai-security-speed-mismatch 等
Pending Jean review
- product-trends/agent-complexity-less-is-more —
ai_draftcandidate(1 source);suggested action: keep draft / verify / mark hypothesis / 或与 Dreamer 合并。
[2026-08-14] ingest | AI 简报 2026-08-14 Afternoon
Pages touched: harness-engineering/self-evolving-harness-composability, harness-engineering/lightweight-vs-orchestration-harness, ai-ecosystem/deepseek-v4, claude-code/overview, product-trends/environment-context-agents Key additions: Pi Agent vs DeepSeek Harness 的架构哲学对比;DeepSeek V4-Pro 正式发布细节;Claude Code 2.1.232 更新;ChatGPT Computer History 环境上下文扩展。 Files processed:
- AI 简报 2026-08-14 Afternoon → 5 个现有 wiki 页面
[2026-08-14] absorb | AI Briefing 2026-08-14 Evening
Pages touched: Self-Evolving Harness Composability, Lightweight vs Orchestration Harness, Harness Engineering Overview, Claude Code Overview, Zhipu GLM-5 Scaling Pain, Product Trends Overview Key additions: DSH 生态新证据(event sourcing、REPL、PenguinHarness、64 天 commit 数据);Pi Agent 作者反应与 token 成本对比;Claude Code 质量 postmortem 与 Managed Agents 企业扩展;GLM-5.3 后训练 RL 跃迁;agentic web 与 MCP/NL Web 协议定位。 Files processed: AI 简报 2026-08-14 晚间
[2026-08-14] absorb | AI Briefing 2026-08-14 (evening)
Pages touched: harness-engineering/self-evolving-harness-composability, harness-engineering/agentic-software-is-systems-engineering, product-trends/environment-context-agents, harness-engineering/loop-engineering Key additions: DSH/Cordis 多角度验证、34-agent workforce 系统工程模式、Agent 产品记忆+工具+编排器架构收敛、OpenCode2 插件化 loop substrate。 Files processed:
[2026-08-13] absorb | newsletter 2026-08-13
Files processed: 2 Pages touched: grok-4-6(新建), ai-security-speed-mismatch, agentic-infrastructure, zero-trust-ai-agents, ramp-ai-adoption-playbook, agents-md-as-contract Key additions: HF 智能体入侵(机器速度攻击完整案例)与 Vercel deepsec 防守窗口 → ai-security-speed-mismatch;Kevin Scott 智能体互联网 → agentic-infrastructure;HF 入侵零信任印证 → zero-trust-ai-agents;Fable 5 采用疲软与价格上限 → ramp-ai-adoption-playbook;Instruction Budget 与配置资产化 → agents-md-as-contract;Grok 4.6 实体页(candidate/ai_draft)。 Decisions: 2×absorbed(absorb_now);语音礼仪与内容水印溯源作为 idea_candidate 留待跨源涌现。
[2026-08-13] absorb | evening briefing + digest
Files processed: 2 Pages touched: self-evolving-harness-composability(新建), deepseek-v4, agents-md-as-contract, claude-managed-agents-cookbook, jevons-paradox-ai-scope-expansion, harness-engineering overview Key additions: DeepSeek V4-Pro 正式发布与峰谷定价调整(deepseek-v4);DeepSeek Harness 开源 + 北大时空可组合性论文 → 新建概念页 self-evolving-harness-composability;"CLAUDE.md 为什么只增不减"论文 → agents-md-as-contract;Managed Agents 大脑/手解耦架构 + 自托管 sandbox + MCP tunnel → claude-managed-agents-cookbook;Levie Jevons 实例 → jevons-paradox-ai-scope-expansion;harness MOC 增加 self-evolving harness 概念与判断。 Decisions: 2×absorbed(absorb_now)。
[2026-08-12] absorb | last 30 days
Files processed: 0 Pages touched: wiki/index.md, wiki/_backlinks.json Key additions: No new raw files in the last 30 days; rebuilt index and backlinks. Updated last_absorb.
[2026-07-29] wiki-daily-update | No new raw files; index rebuilt
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned raw/ for .md files newer than last absorb timestamp (2026-07-22T16:47:00Z): 0 found. Hash-checked all raw .md files against _absorb_log.json: 0 missing, 0 changed. Rebuilt index.md (440 pages, 4 MOCs, 100 pending review) and _backlinks.json (924 targets). No witness prompts generated because no new pages or raw files were absorbed. Files processed: none Prompts: none
[2026-07-27] wiki-daily-update | No new raw files; index rebuilt
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned raw/ for .md files modified in last 24h/7d: 0 found. Rebuilt index.md (440 pages, 4 MOCs, 100 pending review) and _backlinks.json (924 targets). Generated prompts for witness from today's life-wiki drift and weekly insight reports. Files processed: none Prompts: Prompts for Witness — 2026-07-27
[2026-07-26] EMERGE | raw emergent themes
Range: 2026-07-12 to 2026-07-26 Sources scanned: 0 Sources cited: 0 Report: 2026-07-26 Raw Emergent Themes Key additions: No raw files modified in the last 14 days. Most recent raw files are 2026-06-28/29. Pending Jean review on whether to run a catch-up range.
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned 7 markdown files under raw/ modified in the last 30 days; all 7 were already absorbed (SHA256 matched). Regenerated index.md (441 pages, 11 sections, 4 MOCs, 100 pending review) and _backlinks.json (993 targets). Pilot MOCs present. Files processed: none (all candidates already absorbed)
[2026-07-25] absorb | Rebuilt indexes, no new raw files
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned 7 markdown files under raw/ modified in the last 30 days; all 7 were already absorbed (SHA256 matched). Regenerated index.md (440 pages, 10 sections, 4 MOCs) and _backlinks.json (925 backlinks). Pilot MOCs present. Files processed: none (all candidates already absorbed)
[2026-07-23] wiki-daily-update | No new raw files
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned 762 markdown files under raw/; all already absorbed and SHA256 matched. Refreshed QMD index (1 new, 15 updated, 1662 unchanged; embedded 77 chunks from 16 docs). Regenerated index.md (440 pages) and _backlinks.json (996 targets). No new prompts generated. Files processed: none
[2026-07-22] wiki-daily-update | No new raw files
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned 762 markdown files under raw/; all already absorbed and SHA256 matched. Refreshed QMD index (3 new, 20 updated, 1654 unchanged; embedded 132 chunks from 23 docs). Regenerated index.md (440 pages, 11 sections) and _backlinks.json (945 targets). No new prompts generated. Files processed: none
[2026-07-10] absorb | Rebuilt indexes, no new raw files
Pages touched: Wiki Index, Backlinks Index Key additions: Scanned 39 markdown files under raw/ modified in the last 30 days; all were already absorbed (SHA256 matched). Regenerated index.md (440 pages, 11 sections, 4 MOCs, 100 pending review) and _backlinks.json (924 backlinks). Pilot MOCs present. Files processed: none (all candidates already absorbed)
[2026-07-03] wiki-daily-update | No new raw files in the last 24h
Files discovered
- 0 new markdown files under raw/ in the last 24h
- 5 historical files checked (2026-06-12 batch); all already present in wiki/_absorb_log.json with matching SHA256 hashes (absolute path keys confirmed)
Files absorbed
- None (no new files to process)
QMD refresh
- qmd update && qmd embed executed
- Files indexed: 3 new, 2 updated, 1669 unchanged
- Vectors embedded: 22 chunks from 5 documents
Prompts for witness
- Generated 7 prompts based on mature/candidate wiki pages (loop-engineering, compound-engineering, ai-assisted-creative-production)
- File:
outputs/prompts-for-witness-2026-07-03.md
Backlinks and index
- No rebuild required; no new pages or status changes in this run
- wiki/index.md and wiki/_backlinks.json current from 2026-07-02
Notes
- Absorb log contains 14 absolute-path keys (e.g.,
/Users/jean/Documents/Obsidian Vault/raw/...) alongside relative-path keys. This format inconsistency should be normalized on a future cleanup pass.
[2026-07-03] absorb | June 12 raw batch
Pages touched: writing/ai-assisted-creative-production, harness-engineering/loop-engineering, harness-engineering/model-routing, harness-engineering/computer-use-best-practices, mental-models/ai-capability-gap, claude-code/overview Key additions: AI sandwich and Compound Engineering LFG patterns, nested agent recursion, price-speed-vibe framework, dual-track rocket-launcher/daily-driver model strategy, vibe as human differentiator, Computer Use competitive audit, Fable 5 pricing and team adoption notes. Files processed:
- 诗梳风 EP21 → writing/ai-assisted-creative-production
- AI Briefing 2026-06-12 (evening) → harness-engineering/loop-engineering, claude-code/overview
- AINews Loopcraft → harness-engineering/loop-engineering
- Every AI Everywhere → harness-engineering/loop-engineering, harness-engineering/model-routing, mental-models/ai-capability-gap, claude-code/overview
- Ben's Bites Fable → harness-engineering/loop-engineering, harness-engineering/model-routing, harness-engineering/computer-use-best-practices, claude-code/overview
[2026-08-24] ingest | AI Briefing 2026-08-24 Morning
Pages touched: claude-code/overview, harness-engineering/overview, claude-code/what-makes-good-agents-md Key additions: Opus 5 quality concerns, trainable AGENTS.md via backpass, Compound Engineering context reduction, top-down/bottom-up evals, AX-as-UX, Codex /goal quota usage. Files processed:
- AI Briefing 2026-08-24 Morning → claude-code/overview, harness-engineering/overview, claude-code/what-makes-good-agents-md
[2026-08-25] absorb | AI Builders Digest 2026-08-24
Pages touched: harness-engineering/judgment-engineering, product-trends/ai-operator-role, product-trends/cli-as-agent-interface, product-trends/saas-vs-agent-native, forecasts/jevons-paradox-ai-scope-expansion, claude-code/overview Key additions: layered evals (Goldilocks + top-down/bottom-up), AI-fluent assistant case, CLI counterpoint, systems-of-record prediction, Jevons evidence from Sol price drop, Apple Foundation Models Swift package. Files processed:
- AI Builders Digest 2026-08-24 → harness-engineering/judgment-engineering, product-trends/ai-operator-role, product-trends/cli-as-agent-interface, product-trends/saas-vs-agent-native, forecasts/jevons-paradox-ai-scope-expansion, claude-code/overview
[2026-08-25] absorb | Every — Life After Automation
Pages touched: harness-engineering/ai-cost-governance, product-trends/ai-tool-build-vs-buy-decision, writing/writing-with-ai, product-trends/org-design-ai-age, harness-engineering/multi-agent-coordination-patterns, harness-engineering/what-is-agent-harness, product-trends/living-software-framework Key additions: Promoted AI cost governance to mature; added Naveen Naidu dispatch desk case; added Every frontier team and one-person agent team to org design; added harness-gets-simpler trend; added malleable software / Homer car section. Files processed:
- Every — Life After Automation → multiple wiki pages
[2026-08-25] absorb | AI Briefing 2026-08-25 Afternoon
Pages touched: harness-engineering/prompt-caching, claude-code/overview, ai-ecosystem/overview Key additions: 补充了模型切换导致 prompt cache 失效、Codex/Cursor skill 实践、Tibo 访谈中 ChatGPT-Codex 合并与 cloud agent 判断。 Files processed:
- AI Briefing 2026-08-25 Afternoon → harness-engineering/prompt-caching, claude-code/overview, ai-ecosystem/overview
[2026-08-26] absorb | Every — I Tried the AI Model Built to Fix AI Writing
Pages touched: writing/ai-writing-distribution, writing/ai-writing-style-signals, writing/writing-with-ai, writing/overview Key additions: Created candidate concept on AI writing distribution problem; promoted AI Writing Style Signals to mature; added local-editing-right and strict-mode observations to Writing With AI. Files processed:
[2026-08-26] absorb | AI Briefing 2026-08-26 morning
Pages touched: claude-code/agents-md-as-contract, claude-code/overview, ai-tools/overview, harness-engineering/model-routing Key additions: AGENTS.md/CLAUDE.md split-brain and hackability turn, skill-to-skill invocation protocol, sensitive-domain skill design, GPT-5.6 /goal personality risk, Vercel Run SDK and Sentinel in tool radar, specialist/personality-aware model routing. Files processed:
- AI Briefing 2026-08-26 morning → claude-code/agents-md-as-contract, claude-code/overview, ai-tools/overview, harness-engineering/model-routing
[2026-08-27] ingest | Every — Benchmarks Don't Know Your Job
Pages touched: harness-engineering/judgment-engineering, harness-engineering/model-routing, harness-engineering/agentic-infrastructure, harness-engineering/agent-trust-verification, harness-engineering/overview Key additions: real-work evals as a routing/judgment input; Cursor Continuity for agent-generated repos; fences as policy-based trust boundary. Files processed:
- Every — Benchmarks Don't Know Your Job → Judgment Engineering, Model Routing, Agentic Infrastructure, Agent Trust Verification, Harness Engineering Overview
[2026-08-28] absorb | AI Briefing 2026-08-28 Morning
Pages touched: harness-engineering/ai-security-speed-mismatch, ai-ecosystem/hermes-agent, harness-engineering/model-routing Key additions: OpenAI/Sam cyber-defense window, Hermes real-profile browsing, and Replit/OctoLoop routing signals. Files processed:
- AI Briefing 2026-08-28 Morning -> harness-engineering/ai-security-speed-mismatch, ai-ecosystem/hermes-agent, harness-engineering/model-routing
[2026-08-28] absorb | AI Briefing 2026-08-28 Afternoon
Pages touched: claude-code/overview, harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, harness-engineering/self-verification-loops, harness-engineering/self-evolving-harness-composability, harness-engineering/model-routing Key additions: Claude Code artifacts as live status surface; Anthropic containment as blast-radius control; WebMCP as action-readable websites; eval plus acceptance standards before agent implementation; feedback-to-skill PR loop; GLM-5.3-Flash price-quality routing follow-up. Files processed:
- AI Briefing 2026-08-28 Afternoon -> absorbed
- AI Builders Digest 2026-08-28 -> skipped_duplicate / raw_only because merged into the afternoon briefing
Pending Jean review:
- claude-code/overview -
ai_draft; suggested action: keep draft or verify the Claude Code artifacts and scientists-plan details. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: keep draft or verify containment details against the Anthropic source. - product-trends/agent-native-architecture -
ai_draft; suggested action: keep draft or verify WebMCP terminology. - harness-engineering/self-verification-loops -
ai_draft; suggested action: keep draft or convert eval/acceptance rules into a task checklist. - harness-engineering/self-evolving-harness-composability -
ai_draft; suggested action: keep draft or verify the Warp workflow source. - harness-engineering/model-routing -
ai_draft; suggested action: keep draft or independently reproduce the GLM-5.3-Flash benchmark.
[2026-08-28] ingest | AI Briefing 2026-08-28 Evening
Pages touched: harness-engineering/self-evolving-harness-composability, harness-engineering/self-verification-loops, claude-code/agents-md-as-contract, product-trends/agent-native-architecture Key additions: Pi 的分层 Harness 与 single-writer 规则、独立 Definition of Done、植入 Bug 评测的覆盖率/成本维度,以及 WebMCP notebook 的人机协作形态。普通产品公告和未独立核验的数字保留在 raw。 Files processed:
- AI Briefing 2026-08-28 Evening → selective absorb into the four pages above
[2026-08-29] absorb | AI Briefing 2026-08-29 Morning
Pages touched: ai-ecosystem/ai-data-licensing-market, ai-ecosystem/openai-codex-superapp, product-trends/saas-vs-agent-native Key additions: Google Expert Intelligence as trusted-source packaging, ChatGPT Work life-service tasks with credential boundary, and context migration friction as an adoption gate for new AI products. Repeated AI cyber-defense, Hermes real-profile browsing, and Replit/OctoLoop routing signals stayed raw-only because they were already absorbed from 2026-08-28. Files processed:
- AI Briefing 2026-08-29 Morning -> ai-ecosystem/ai-data-licensing-market, ai-ecosystem/openai-codex-superapp, product-trends/saas-vs-agent-native
Pending Jean review:
- ai-ecosystem/ai-data-licensing-market -
ai_draft; suggested action: keep draft or verify the Google Expert Intelligence source details. - ai-ecosystem/openai-codex-superapp -
ai_draft; suggested action: keep draft or verify ChatGPT Work credential-boundary claims. - product-trends/saas-vs-agent-native -
ai_draft; suggested action: keep draft or verify the context-migration friction signal against primary product adoption evidence.
[2026-08-29] absorb | Every — 33 Questions Executives Ask About AI—Answered
Pages touched: product-trends/ai-adoption-levels, product-trends/org-design-ai-age, harness-engineering/judgment-engineering Key additions: 将 AI 采用从个人工具层级校准为组织采用路径,补充 champion、真实工作产物培训、责任边界和 coverage/stability/residual work 评估。 Files processed:
- Every — 33 Questions Executives Ask About AI—Answered → product-trends/ai-adoption-levels, product-trends/org-design-ai-age, harness-engineering/judgment-engineering
Pending Jean review:
- product-trends/ai-adoption-levels —
ai_draft; suggested action: verify the enterprise adoption calibration against additional organizations. - product-trends/org-design-ai-age —
ai_draft; suggested action: verify the champion and artifact-based training claims. - harness-engineering/judgment-engineering —
ai_draft; suggested action: define task-specific thresholds for coverage, stability, and residual work.
[2026-08-29] absorb | Ben’s Bites — How I built this
Pages touched: claude-code/overview Key additions: 将截图标注反馈循环记录为 agent review surface,连接设计判断、原始文件和短指令,并保留行为与安全验收边界。 Files processed:
Pending Jean review:
- claude-code/overview —
ai_draft; suggested action: keep draft or verify whether screenshot feedback should become a reusable design workflow.
[2026-08-29] absorb | AI Briefing afternoon
Pages touched: product-trends/token-capital, harness-engineering/model-routing, claude-code/self-improving-skills, harness-engineering/agent-trust-verification Key additions: Added model-access continuity as token capital, provider/cost fallback routing evidence, Warp and Skill Doctor signals for self-improving skills, and legitimate-access agent risks for enterprise data and real accounts. Files processed:
- AI Briefing 2026-08-29 Afternoon → product-trends/token-capital, harness-engineering/model-routing, claude-code/self-improving-skills, harness-engineering/agent-trust-verification
- AI Builders Digest 2026-08-29 → skipped_duplicate / raw_only because it was merged into the afternoon briefing
Pending Jean review
- product-trends/token-capital —
ai_draft; suggested action: keep draft or verify the Cursor/OpenAI access-continuity interpretation. - harness-engineering/model-routing —
ai_draft; suggested action: keep draft or verify the Pawel Huryn benchmark claims before using them for routing defaults. - claude-code/self-improving-skills —
ai_draft; suggested action: keep draft or decide whether the page should stay mature after adding the second briefing source. - harness-engineering/agent-trust-verification —
ai_draft; suggested action: keep draft or mark the delegated-real-account section as hypothesis until more sources accumulate.
[2026-08-29] absorb | AI Briefing 2026-08-29 Evening
Pages touched: claude-code/overview, harness-engineering/dhh-agentic-engineering, harness-engineering/agentic-software-is-systems-engineering, product-trends/agent-native-architecture, harness-engineering/model-routing, harness-engineering/agent-trust-verification Key additions: Claude Code 产品控制面、DHH 多机 Agent session、软件与 Agent 的确定性护栏、Agent-native Web 分层、经济性驱动的模型路由,以及真实账号操作的信任边界。 Files processed:
- AI Briefing 2026-08-29 Evening -> selective absorb into the six pages above; ordinary announcements, repeated Cursor/OpenAI coverage, and unverified claims remain raw-only.
Pending Jean review:
- claude-code/overview -
ai_draft; suggested action: keep draft or verify the Claude Code release details and provider-boundary interpretation. - harness-engineering/dhh-agentic-engineering - source-derived; suggested action: verify the multi-machine setup from a primary source.
- harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: verify the software-and-agent deployment claims with additional sources. - product-trends/agent-native-architecture -
ai_draft; suggested action: verify the human-interface / agent-interface split. - harness-engineering/model-routing -
ai_draft; suggested action: reproduce routing trade-offs on a local task set. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: verify the account-automation and phishing details before generalizing.
[2026-08-29] absorb correction | AI Briefing 2026-08-29 Evening
The briefing source URL check found and corrected two provenance mismatches before finalization. The Obsidian raw file was re-read after correction; the six previously touched wiki pages did not need content changes, only the absorb record hash was refreshed. All remaining X source URLs match the merged evening timeline.
[2026-08-30] wiki-absorb | 0 new files, indexes rebuilt
Scan range
- Last 30 days (default)
- 225 markdown files under raw/ matched mtime criteria
Result
- 0 unprocessed files (all path + hash matched existing absorb log entries)
- 0 changed files
Maintenance
- Rebuilt wiki/index.md (451 pages)
- Rebuilt wiki/_backlinks.json (1240 targets)
Pending Jean review
- None from this run
[2026-08-30] absorb | AI Briefing 2026-08-30 Morning
Pages touched: harness-engineering/model-routing, product-trends/token-capital, product-trends/token-optimization-economics, claude-code/self-improving-skills, product-trends/agent-native-architecture Key additions: Added owned evals for model-agnostic routing, Codex orchestration waste as quota economics, skill memory lifecycle control, and AI Native workflow split. Files processed:
- AI Briefing 2026-08-30 Morning -> harness-engineering/model-routing, product-trends/token-capital, product-trends/token-optimization-economics, claude-code/self-improving-skills, product-trends/agent-native-architecture
Pending Jean review
- harness-engineering/model-routing -
ai_draft; suggested action: keep draft or test model-agnostic routing on Jean-specific tasks. - product-trends/token-capital -
ai_draft; suggested action: keep draft or verify whether language-specific evals belong in the concept. - product-trends/token-optimization-economics -
ai_draft; suggested action: keep draft or compare Codex quota-waste categories against local automation logs. - claude-code/self-improving-skills -
ai_draft; suggested action: keep draft or decide whether rule-demotion belongs in skill maintenance checklists. - product-trends/agent-native-architecture -
ai_draft; suggested action: keep draft or turn the AI Native workflow test into a checklist.
[2026-08-30] absorb | AI Briefing 2026-08-30 Afternoon
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/agent-memory-vs-context-substrate, harness-engineering/agent-harness-engineering-addy-osmani, product-trends/token-capital Key additions: Added ruin-first agent safety, cloud-login trust boundary, current-state memory compilation, fundamentals-as-tradeoff-interface, and compute-scarcity token-capital pressure. Files processed:
- AI Briefing 2026-08-30 Afternoon -> harness-engineering/agent-trust-verification, harness-engineering/agent-memory-vs-context-substrate, harness-engineering/agent-harness-engineering-addy-osmani, product-trends/token-capital
- AI Builders Digest 2026-08-30 -> skipped_duplicate / raw_only because it was merged into the afternoon briefing
Pending Jean review
- harness-engineering/agent-trust-verification -
ai_draft; suggested action: keep draft or define local blast-radius tiers for agent actions. - harness-engineering/agent-memory-vs-context-substrate - source-derived; suggested action: decide whether current-state compilation deserves its own concept page after more sources.
- harness-engineering/agent-harness-engineering-addy-osmani -
ai_draft; suggested action: keep draft or turn tradeoff-interface review into a reusable checklist. - product-trends/token-capital -
ai_draft; suggested action: keep draft or compare compute-scarcity claims against future pricing evidence. - product-trends/token-capital -
ai_draft; suggested action: keep draft or compare compute-scarcity claims against future pricing evidence.
[2026-08-30] absorb | AI Briefing 2026-08-30 Evening
Pages touched: claude-code/agents-md-as-contract, claude-code/self-improving-skills, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, product-trends/agent-native-architecture, product-trends/saas-vs-agent-native, ai-ecosystem/ai-chip-architecture Key additions: Added proportional AGENTS.md scope rules, skill-memory lifecycle control, fundamentals and harness minimalism, bounded verification, code-to-business moat evidence, and accelerator data-movement tradeoffs. Files processed:
- AI Briefing 2026-08-30 Evening -> claude-code/agents-md-as-contract, claude-code/self-improving-skills, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, product-trends/agent-native-architecture, product-trends/saas-vs-agent-native, ai-ecosystem/ai-chip-architecture
Pending Jean review
- claude-code/agents-md-as-contract - ai_draft; suggested action: keep draft, verify the full Voxyz_ai thread, or extract a project-specific scope rule.
- claude-code/self-improving-skills - ai_draft; suggested action: define promotion and demotion criteria for one recurring skill.
- harness-engineering/agentic-software-is-systems-engineering - ai_draft; suggested action: map one active project against the five skill areas.
- harness-engineering/self-verification-loops - ai_draft; suggested action: turn bounded review into a project checklist.
- product-trends/agent-native-architecture - ai_draft; suggested action: decide whether the code-to-business moat belongs in saas-vs-agent-native.
- product-trends/saas-vs-agent-native - ai_draft; suggested action: compare the claim with evidence from actual retention and workflow ownership.
- ai-ecosystem/ai-chip-architecture - ai_draft; suggested action: verify architecture descriptions against vendor and independent sources.
[2026-08-31] absorb | Daily absorb run (last 30 days)
Pages touched: none Key additions: No unprocessed files found; all 229 candidate raw files already present in _absorb_log.json with matching SHA256 hashes. Rebuilt index (451 pages) and backlinks (1246 targets). Files processed:
- none
[2026-08-31] absorb | AI Briefing 2026-08-31 Morning
Pages touched: ai-ecosystem/openai-codex-superapp, harness-engineering/ai-security-speed-mismatch, forecasts/jevons-paradox-ai-scope-expansion, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/lightweight-vs-orchestration-harness Key additions: Added ChatGPT Work/Codex platform-surface evidence, autonomous security mechanism framing, enterprise token-demand expansion, scope-control engineering practice, and Pi extension-stack tradeoffs. Files processed:
- AI Briefing 2026-08-31 Morning -> ai-ecosystem/openai-codex-superapp, harness-engineering/ai-security-speed-mismatch, forecasts/jevons-paradox-ai-scope-expansion, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/lightweight-vs-orchestration-harness
Pending Jean review
- ai-ecosystem/openai-codex-superapp -
ai_draft; suggested action: keep draft or verify the Cursor/OpenAI access dispute against primary statements. - harness-engineering/ai-security-speed-mismatch -
ai_draft; suggested action: keep draft or separate incident facts from anthropomorphic interpretation in a future review. - forecasts/jevons-paradox-ai-scope-expansion -
ai_draft; suggested action: keep draft or compare Levie's claim against observed token usage in local workflows. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: keep draft or test Scope Guard against one recurring coding task. - harness-engineering/lightweight-vs-orchestration-harness -
ai_draft; suggested action: keep draft or benchmark one Pi extension before adopting it by default.
[2026-08-31] absorb | AI Briefing 2026-08-31 Afternoon
Pages touched: harness-engineering/model-routing, product-trends/token-capital, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-evolving-harness-composability Key additions: model optionality, quota transparency, credential lifecycle completeness, AI-code change-axis architecture, and shared-agent orchestration. Files processed:
- AI Briefing 2026-08-31 Afternoon → absorbed_now
- AI Builders Digest 2026-08-31 → skipped_duplicate/raw_only because it was merged into the briefing
Pending Jean review
- harness-engineering/model-routing —
ai_draft; suggested action: keep draft or test open/local fallback paths on a small task set. - product-trends/token-capital —
ai_draft; suggested action: keep draft or decide whether quota transparency needs a separate governance checklist. - harness-engineering/agent-trust-verification —
ai_draft; suggested action: keep draft or verify the cloud-login and credential-lifecycle examples before generalizing. - harness-engineering/agentic-software-is-systems-engineering —
ai_draft; suggested action: keep draft or compare one current project against the change-axis architecture checklist. - harness-engineering/self-evolving-harness-composability —
ai_draft; suggested action: keep draft or verify OpenClaw shared-agent workflow details.
[2026-08-31] absorb | AI Briefing 2026-08-31 Evening
Pages touched: harness-engineering/self-verification-loops, claude-code/agents-md-as-contract, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture, ai-ecosystem/qwen-36-agent-leap, claude-code/awesome-design-skill
Key additions: The evening Twitter-only briefing added reusable evidence about adversarial verification, the separation of Rules and Skills, outcome-level AI cost accounting, agent-native operating metrics, compound model efficiency, and reusable visual design systems.
Files processed:
- AI Briefing 2026-08-31 Evening → selective updates to existing concept and tool pages; ordinary news remains raw-only.
[2026-09-01] absorb | AI Briefing 2026-09-01 Morning
Pages touched: ai-ecosystem/openai-codex-superapp, harness-engineering/ai-security-speed-mismatch, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-cost-governance, harness-engineering/agent-memory-vs-context-substrate, claude-code/awesome-design-skill
Key additions: Added ChatGPT Work steering-surface evidence, evaluation/training environment security boundaries, AI-code maintainability practice, token-waste controls, restart-resilient agent memory, and reusable visual design-system acceptance.
Files processed:
- AI Briefing 2026-09-01 Morning → selective updates to existing concept and tool pages; ads, sports, jokes, and one-off announcements remain raw-only.
Pending Jean review
- ai-ecosystem/openai-codex-superapp -
ai_draft; suggested action: keep draft or verify ChatGPT Work steering claims against primary product material. - harness-engineering/ai-security-speed-mismatch -
ai_draft; suggested action: keep draft or review Anthropic's primary incident write-up before treating it as a settled case study. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: test one current project against misleading-success regression cases. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: measure one automation by model, context, tool calls, and accepted output. - harness-engineering/agent-memory-vs-context-substrate -
ai_draft; suggested action: test restart recovery on one long-running workflow. - claude-code/awesome-design-skill -
ai_draft; suggested action: run a three-format visual Skill acceptance test.
[2026-09-01] absorb | AI Briefing 2026-09-01 Afternoon
Pages touched: harness-engineering/continual-learning, harness-engineering/model-routing, harness-engineering/agent-trust-verification, product-trends/software-soul-ai-slop, product-trends/agent-native-architecture, ai-ecosystem/openai-codex-superapp Key additions: absorbed afternoon signals on continual learning, token governance, reporting readability, slop reduction, agent-native Work/WebMCP surfaces, and Codex/ChatGPT Work product direction. Files processed:
- AI Briefing 2026-09-01 Afternoon → absorbed / absorb_now
- AI Builders Digest 2026-09-01 → skipped_duplicate / raw_only; merged into afternoon briefing
[2026-09-02] absorb | AI Briefing 2026-09-02 Morning
Pages touched: harness-engineering/ai-security-speed-mismatch, harness-engineering/model-routing, claude-code/context-window-optimization, claude-code/claude-design, product-trends/human-agent-interaction, ai-ecosystem/qwen-36-agent-leap, product-trends/agent-native-architecture
Key additions: Added Astra safety-gated cyber rollout, Fable 5.1 routing and cache economics, Qwen3.8-Max frontier coding claims, Claude Design prototype critique loops, less-annoying agent UX, and WebMCP/Sider/MCPX execution-surface signals.
Files processed:
- AI Briefing 2026-09-02 Morning -> absorbed / absorb_now
Pending Jean review
- harness-engineering/ai-security-speed-mismatch -
ai_draft; suggested action: verify Astra cyber-access gating against OpenAI primary launch material. - harness-engineering/model-routing -
ai_draft; suggested action: reproduce Fable 5.1 and Qwen3.8-Max routing trade-offs on a local task set. - claude-code/context-window-optimization -
ai_draft; suggested action: confirm 1M-context and compact timing with actual Claude Code billing or usage logs. - claude-code/claude-design -
ai_draft; suggested action: decide whether BaoCut-style critique loops belong in a reusable design checklist. - product-trends/human-agent-interaction -
ai_draft; suggested action: keep or operationalize less-annoying agents as an interaction audit. - ai-ecosystem/qwen-36-agent-leap -
ai_draft; suggested action: verify Qwen3.8-Max numbers against release docs and third-party evals. - product-trends/agent-native-architecture -
ai_draft; suggested action: review external execution-surface risks before treating MCPX/Sider as durable architecture.
[2026-09-03] absorb | AI Briefing 2026-09-02 Evening
Pages touched: harness-engineering/self-evolving-harness-composability, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/multi-agent-coordination-patterns, harness-engineering/self-verification-loops, claude-code/awesome-design-skill, harness-engineering/continual-learning, harness-engineering/agent-memory-vs-context-substrate, harness-engineering/ai-cost-governance Key additions: Added specialized agent workforce, shared work ledgers, proof artifacts, operational postmortems, design exploration and explicit urgency-cost evidence; repeated briefing items remain raw-only. Files processed:
- AI Briefing 2026-09-02 Evening -> selective updates to existing concept pages; ordinary announcements, rumors, promotions and duplicate signals remain raw-only.
Pending Jean review
- harness-engineering/self-evolving-harness-composability — status ai_draft; suggested action: verify the Grok Bot workflow or downgrade source-only.
- harness-engineering/agentic-software-is-systems-engineering — status ai_draft; suggested action: map one active workflow to workforce, state, feedback, and acceptance layers.
- harness-engineering/multi-agent-coordination-patterns — status ai_draft; suggested action: compare specialized roles with a single-agent baseline.
- harness-engineering/self-verification-loops — status ai_draft; suggested action: turn proof artifacts and traffic reconciliation into an acceptance checklist.
- claude-code/awesome-design-skill — status ai_draft; suggested action: test exploration and cleanup stages on three visual formats.
- harness-engineering/continual-learning — status ai_draft; suggested action: define promotion and rollback criteria for one playbook rule.
- harness-engineering/agent-memory-vs-context-substrate — status ai_draft; suggested action: test restart and reconciliation recovery with one external work ledger.
- harness-engineering/ai-cost-governance — status ai_draft; suggested action: measure monitoring frequency, token spend, and accepted outcomes for one urgent workflow.
[2026-09-03] absorb | AI Briefing 2026-09-03 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/multi-agent-coordination-patterns, product-trends/agent-native-architecture, ai-ecosystem/hermes-agent
Key additions: Added task-level model routing metrics, event-triggered agent authority boundaries, WebMCP tool-discovery-before-browser-fallback, Octoloop coordination caveats, and Hermes remote-instance/model-access updates.
Files processed:
- AI Briefing 2026-09-03 Afternoon -> absorbed / absorb_now; Follow Builders was skipped because the upstream feed was still dated 2026-09-02.
Pending Jean review
- harness-engineering/model-routing -
ai_draft; suggested action: test task cost, task time, effort level, and cache behavior on one local task set. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: define approval tiers for email-triggered agents, cloud login, payment methods, and credential lifecycle tests. - harness-engineering/multi-agent-coordination-patterns -
ai_draft; suggested action: verify Octoloop and WebMCP behavior before adopting either as workflow guidance. - product-trends/agent-native-architecture -
ai_draft; suggested action: turn capability discovery, browser fallback, and auditability into product tests. - ai-ecosystem/hermes-agent -
ai_draft; suggested action: verify Hermes v0.21.0 remote-instance boundaries before using them.
[2026-09-03] absorb | AI Briefing 2026-09-03 Evening
Pages touched: claude-code/awesome-design-skill, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, claude-code/self-improving-skills, harness-engineering/ai-cost-governance, harness-engineering/model-routing, product-trends/agent-native-architecture, harness-engineering/browser-harness, harness-engineering/compound-engineering Key additions: Added reusable evidence on Markdown design systems, goal-path-execution controls, ablation and E2E verification, skill drift, task-level cost metrics, workflow-level model routing, WebMCP and Agent browser surfaces, and context-first compound writing; announcements, promotions, sports, and low-substance replies remain raw-only. Files processed:
- AI Briefing 2026-09-03 Evening -> absorbed / absorb_now
Pending Jean review
- claude-code/awesome-design-skill -
ai_draft; suggested action: test a small DESIGN.md against three product surfaces. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: map one active project against goal alignment, path exploration, and execution traceability. - harness-engineering/self-verification-loops -
ai_draft; suggested action: add an ablation pass and one user-path E2E check to a current AI coding task. - claude-code/self-improving-skills -
ai_draft; suggested action: define a small cross-case regression set for one frequently used skill. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: record task cost, elapsed time, cache hit rate, and acceptance result for one recurring workflow. - harness-engineering/model-routing -
ai_draft; suggested action: choose one workflow and define task-level evals before automating model selection. - product-trends/agent-native-architecture -
ai_draft; suggested action: document the explicit-tool, browser-fallback, and human-approval boundary for one agent workflow. - harness-engineering/browser-harness -
ai_draft; suggested action: compare one browser task on the current harness and an Agent-focused runtime with memory and failure evidence. - harness-engineering/compound-engineering -
ai_draft; suggested action: create one context file and one review skill for a recurring writing task, then inspect the next iteration.
[2026-09-03] absorb | Every — Compound Writing
Pages touched: harness-engineering/compound-engineering, writing/ai-style-guide Key additions: Added context-first writing, inspectable reviewer stages, and the rule that repeated style corrections should compound into reusable context files and workflow rules. Files processed:
- Every — Compound Writing -> absorbed / absorb_now
Pending Jean review
- harness-engineering/compound-engineering -
ai_draft; suggested action: create one context file and one review skill for a recurring writing task, then inspect the next iteration. - writing/ai-style-guide -
ai_draft; suggested action: select one recurring writing task and test a small context pack plus reviewer checklist.
[2026-09-03] absorb | Ben’s Bites — Build your ideas
Pages touched: harness-engineering/self-verification-loops, harness-engineering/agent-trust-verification, ai-ecosystem/model-sovereignty-risk, product-trends/openclaw-getting-started, product-trends/software-soul-ai-slop Key additions: Added independent behavior standards, explicit human-escalation triggers, vendor-access continuity planning, OpenClaw’s minimal workflow, and exploration-mode slop boundaries. Files processed:
- Ben’s Bites — Build your ideas -> absorbed / absorb_now
Pending Jean review
- harness-engineering/self-verification-loops -
ai_draft; suggested action: define one independent behavior standard before a large coding task and compare it with the agent’s own completion claim. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: define escalation rules for approval, missing expertise, high-variance choices, and decisions that require human judgment. - ai-ecosystem/model-sovereignty-risk -
ai_draft; suggested action: verify the vendor-side notice against Cursor and SpaceX primary statements before using it for continuity planning. - product-trends/openclaw-getting-started -
ai_draft; suggested action: prototype one inbox-to-destination workflow with explicit credential and human-handoff boundaries. - product-trends/software-soul-ai-slop -
ai_draft; suggested action: define when an exploratory AI output must pass a quality, rights, and human-taste gate before reuse.
[2026-09-03] absorb | AI Briefing 2026-09-03 Morning
Pages touched: harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-security-speed-mismatch, harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/frontier-code-benchmark, ai-ecosystem/meta-muse-spark, claude-code/context-window-optimization, claude-code/personal-agent-minimal-setup, ai-tools/overview Key additions: Added Twitter-only evidence on AI-native engineering, effort-and-cost routing, credential boundaries, cross-model verification, Muse Spark 1.3, Claude Code context overhead, bounded personal agents, and current tools. Files processed:
- AI Briefing 2026-09-03 Morning -> absorbed / absorb_now
Pending Jean review
- harness-engineering/agentic-software-is-systems-engineering - ai_draft; map one active project against goal, path, execution, and bounded roles.
- harness-engineering/ai-security-speed-mismatch - verify the model-security claims against primary evaluation material.
- harness-engineering/model-routing - define a local matrix for effort, cost, quota continuity, and cross-family verification.
- harness-engineering/agent-trust-verification - add cross-family review and credential-use evidence to an acceptance checklist.
- harness-engineering/frontier-code-benchmark - define hidden-bug and relevance checks before treating fix counts as a benchmark.
- ai-ecosystem/meta-muse-spark - verify Muse Spark 1.3 claims against release documentation.
- claude-code/context-window-optimization - measure one post-upgrade session before changing context or MCP defaults.
- claude-code/personal-agent-minimal-setup - test bounded responsibility on one personal workflow.
[2026-09-03] absorb | AI Briefing 2026-09-03 Afternoon 17-44
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-trust-verification, writing/writing-with-ai, product-trends/agent-native-architecture, harness-engineering/ai-engineering-culture-stack, ai-ecosystem/hermes-agent Key additions: Added scheduled-afternoon evidence on quota-aware routing, subagent orchestration, cross-family verification, Compound Writing, Site Tools, AI engineering culture, and Hermes recursive subagent stress testing. Files processed:
2026-09-04 00:50 | EMERGE | raw emergent themes (last 7 days, 32 sources) | outputs/ideas/2026-09-04-raw-emergent-themes.md
[2026-09-04] absorb | Last 30 days scan (0 new files)
Files scanned: 245 raw markdown files (to-learn, briefing, newsletters, twitter, tools) All 245 already in _absorb_log.json with matching SHA256: 125 absorbed, 90 idea_candidate (emerge_later), 24 skipped_one_off, 6 skipped_duplicate. No page changes. Emergence spot-check: Fable 5 / GPT-5.6 / loops / software-factory themes already covered in existing pages (ai-ecosystem/overview, loop-engineering, software-factory-ladder, openai-codex-superapp). Checkpoint flags: claude-code/context-window-optimization.md (183 lines) and claude-code/self-improving-skills.md (155 lines) exceed 150-line threshold; both grown via dated addenda, consolidation candidate for wiki-cleanup.
[2026-09-04] absorb | AI Briefing 2026-09-04 Morning
Pages touched: ai-ecosystem/overview, harness-engineering/ai-security-speed-mismatch, harness-engineering/model-routing, claude-code/context-window-optimization, claude-code/overview, writing/ai-style-guide
Key additions: Added Astra launch and task-fit evidence, safety-gated cyber rollout details, quota and access continuity as routing inputs, cross-window context and cache diagnostics, Claude Code 2.1.260 and ant apply updates, and de-flavoring as a writing review step. Repeated announcements, promotions, and low-substance reactions remain raw-only.
Files processed:
- AI Briefing 2026-09-04 Morning -> absorbed / absorb_now; Twitter timeline only, no Follow Builders merge.
Pending Jean review
- ai-ecosystem/overview -
ai_draft; suggested action: verify Astra launch claims and comparative model feedback against primary sources and local tests. - harness-engineering/ai-security-speed-mismatch -
ai_draft; suggested action: verify Astra cyber evaluation and production monitoring claims against the primary model card. - harness-engineering/model-routing -
ai_draft; suggested action: test Astra, Fable, and Sol on one fixed task while recording cost, time, quota pool, and review result. - claude-code/context-window-optimization -
ai_draft; suggested action: measure one long session with cross-window notes or cache diagnostics before changing defaults. - claude-code/overview -
ai_draft; suggested action: verify 2.1.260 andant applybehavior in a non-production environment. - writing/ai-style-guide -
ai_draft; suggested action: test the de-flavoring method on one recurring draft and compare voice, precision, and boilerplate.
[2026-09-04] absorb | Ben's Bites — Fable 5.1
Pages touched: ai-ecosystem/anthropic-mythos, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture
Key additions: Added Fable 5.1 cost and benchmark evidence, explicit system-prompt policy changes, build-loop quota observations, and background execution plus WebMCP capability-surface signals. No new wiki page was created.
Files processed:
- Ben's Bites — Fable 5.1 -> absorbed / absorb_now
Pending Jean review
- ai-ecosystem/anthropic-mythos -
ai_draft; suggested action: verify Fable 5.1 release numbers against current official model documentation. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: add data volume, quota consumption, and reusable residue to one recurring workflow's cost record. - product-trends/agent-native-architecture -
ai_draft; suggested action: test one background-capable or WebMCP workflow and record capability discovery, isolation, approval, fallback, and cost.
[2026-09-04] absorb | AI Briefing 2026-09-04 Afternoon 17-50
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, product-trends/agent-native-architecture
Key additions: Added afternoon evidence on Fable planner-executor routing, Astra task-fit limits, self-healing agent recovery loops, evaluation oversight after the OpenAI/Hugging Face incident, Stanford agent-engineering curriculum signals, and extensible/visible agent product surfaces.
Files processed:
- AI Briefing 2026-09-04 Afternoon 17-50 -> absorbed / absorb_now
- AI Builders Digest 2026-09-04 -> skipped_duplicate / raw_only; merged into the afternoon briefing.
Pending Jean review
- harness-engineering/model-routing -
ai_draft; suggested action: test one planning-heavy task with Fable planner plus Opus subagents and compare against a single-model run. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: add failure taxonomy and eval-log oversight to one local agent acceptance checklist. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: map one active workflow against decomposition, data, trajectory, memory, evaluation, and reliability. - product-trends/agent-native-architecture -
ai_draft; suggested action: decide whether extension points and visible bot presence should become separate product tests.
[2026-09-04] absorb | AI Briefing 2026-09-04 Evening 23-00
Pages touched: ai-ecosystem/hermes-agent, harness-engineering/multi-agent-coordination-patterns, harness-engineering/frontier-code-benchmark, harness-engineering/model-routing, product-trends/agent-native-architecture, writing/ai-style-guide
Key additions: Added timeline evidence on recursive Hermes cleanup, planner-executor routing, hidden-bug cost evaluation, agent-facing product surfaces, and de-flavoring model prose. Ordinary news and one-off material stayed in raw.
Files processed:
- AI Briefing 2026-09-04 Evening 23-00 -> absorbed / absorb_now
Pending Jean review
- ai-ecosystem/hermes-agent -
ai_draft; suggested action: verify recursive cleanup with logs and a reproducible repository diff. - harness-engineering/multi-agent-coordination-patterns -
ai_draft; suggested action: define recursive depth, stop conditions, and result handoff format. - harness-engineering/frontier-code-benchmark -
ai_draft; suggested action: define hidden-bug, cost-per-fix, and shared-miss checks. - harness-engineering/model-routing -
ai_draft; suggested action: compare single-model and planner-executor runs on one fixed task. - product-trends/agent-native-architecture -
ai_draft; suggested action: test machine-readable evidence, action completion, recovery, and discoverability. - writing/ai-style-guide -
ai_draft; suggested action: test de-flavoring on one recurring draft and compare voice, precision, and boilerplate.
[2026-09-05] absorb | AI Briefing 2026-09-05 Morning 08-14
Pages touched: ai-ecosystem/openai-codex-superapp, ai-ecosystem/hermes-agent, harness-engineering/agentic-software-is-systems-engineering, claude-code/agents-md-as-contract, ai-tools/ai-writing-guardrails, harness-engineering/ai-cost-governance, harness-engineering/agent-trust-verification, harness-engineering/agent-memory-vs-context-substrate
Key additions: Added Twitter-only evidence on Astra's long-running work surface, Harness-aware evaluation, task-level cost, approval-gated rule extraction, de-flavored writing, and agent-facing context.
Files processed:
- AI Briefing 2026-09-05 Morning 08-14 -> absorbed / absorb_now
Routine release announcements, promotions, and low-substance reactions remained raw-only.
Pending Jean review
- ai-ecosystem/openai-codex-superapp -
ai_draft; suggested action: verify one representative long-running workflow before changing the default model or approval boundary. - ai-ecosystem/hermes-agent -
ai_draft; suggested action: verify the Nous Portal model name, access scope, and one end-to-end Hermes task. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: add Harness, effort, context, time, cost, false-positive, and accepted-fix fields to one local model regression test. - claude-code/agents-md-as-contract -
ai_draft; suggested action: pilot approval-gated rule mining in one repository and measure rule noise. - ai-tools/ai-writing-guardrails -
ai_draft; suggested action: test the de-flavoring prompt on one draft and compare style, factuality, and steering effort. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: add task-level cost and accepted-result fields to one recurring workflow cost record. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: define the lowest-risk repository task where agent cleanup can be tested with an explicit rollback path. - harness-engineering/agent-memory-vs-context-substrate -
ai_draft; suggested action: test a bounded context pack with source links, permissions, and an explicit human review step.
[2026-09-05] absorb revalidation | AI Briefing 2026-09-05 Morning 08-14
Pages touched: ai-ecosystem/openai-codex-superapp, ai-ecosystem/hermes-agent, harness-engineering/agentic-software-is-systems-engineering, claude-code/agents-md-as-contract, ai-tools/ai-writing-guardrails, harness-engineering/ai-cost-governance, harness-engineering/agent-trust-verification, harness-engineering/agent-memory-vs-context-substrate
Key additions: Revalidated the final raw briefing after correcting one source handle; the existing durable addenda remain the same and no duplicate Wiki content was added.
Files processed:
- AI Briefing 2026-09-05 Morning 08-14 -> absorbed / absorb_now; final hash refreshed
[2026-09-05] absorb | AI Briefing 2026-09-05 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, harness-engineering/self-verification-loops Key additions: Astra routing, public-write incident disclosure, WebMCP page-local tools, and verification-as-route-selector signals. Files processed:
- AI Briefing 2026-09-05 Afternoon -> absorbed
- AI Builders Digest 2026-09-05 -> skipped_duplicate / raw_only because merged into briefing
Pending Jean review
- harness-engineering/model-routing -
ai_draft; suggested action: test one Astra, Fable 5.1, and GPT-5.6 Sol task while recording Computer Use success, accepted-result cost, and review burden. - harness-engineering/agent-trust-verification -
ai_draft; suggested action: define a disclosure checklist for browser-agent external writes. - product-trends/agent-native-architecture -
ai_draft; suggested action: test one dev-page workflow where Agent discovers page-local tools before browser automation. - harness-engineering/self-verification-loops -
ai_draft; suggested action: classify one current workflow by available verification signals before choosing a model or Agent surface.
[2026-09-05] wiki-breakdown | 结构审计(cron)
Pages touched: outputs/ideas/2026-09-05-wiki-breakdown-audit Key additions: 差量审计。ideas 工作区 36→8;model-routing 488→530;新增修链 5 处(累计 16);候选表沿用 09-04(19 项,待 Jean 审批)。
[2026-09-05] absorb | The Folder Is the Agent
Pages touched: harness-engineering/folder-is-the-agent, harness-engineering/compound-engineering, claude-code/agents-md-as-contract Key additions: Folder context, file-based dispatch, trust-before-orchestration, and layered CLAUDE.md/AGENT.md contracts. Files processed:
- The Folder Is the Agent -> absorbed / absorb_now
[2026-09-05] absorb | Scraping 107M rows of data to build this
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture Key additions: Provenance fingerprints, parked/incomplete states, task-level build cost, static filtering boundaries, and Agent-native data products. Files processed:
- Scraping 107M rows of data to build this -> absorbed / absorb_now
Pending Jean review
- harness-engineering/folder-is-the-agent - ai_draft; suggested action: test one recurring workflow with explicit drift and stall checks before orchestration.
- harness-engineering/compound-engineering - ai_draft; suggested action: compound one review result into the context folder before dispatch.
- claude-code/agents-md-as-contract - ai_draft; suggested action: document one project context reading order and classify stable rules versus institutional memory.
- harness-engineering/agent-trust-verification - ai_draft; suggested action: add source fingerprint, coverage status, filter scope, and current-version checks to one data-report acceptance checklist.
- harness-engineering/ai-cost-governance - ai_draft; suggested action: record one workflow by data volume, model effort, token cost, elapsed time, accepted result, and reusable residue.
- product-trends/agent-native-architecture - ai_draft; suggested action: test a read-only data product for provenance, missing-data states, filter scope, and human review.
[2026-09-06] absorb | AI Briefing 2026-09-05 Evening
Pages touched: harness-engineering/model-routing, harness-engineering/model-harness-fit, product-trends/mid-developer-trap, claude-code/agents-md-as-contract, harness-engineering/multi-agent-coordination-patterns, ai-ecosystem/hermes-agent Key additions: Cache-price vs per-task cost and effort calibration routing inputs; harness-must-be-recorded eval discipline; junior low-blast-radius growth strategy; request-level acceptance boundaries; cross-repo agent orchestration; Hermes cloud-gateway continuation and session resume signals. Files processed:
- AI Briefing 2026-09-05 Evening -> absorbed / absorb_now
Pending Jean review
- harness-engineering/model-routing —
ai_draft; suggested action: record input/output/cache-read price and per-accepted-task cost for one Astra and one Fable 5.1 task. - harness-engineering/model-harness-fit —
ai_draft; suggested action: add harness, context window, and stopping criteria fields to one local model comparison note. - product-trends/mid-developer-trap —
ai_draft; suggested action: keep draft or test the low-blast-radius internal tool pattern on one real project. - claude-code/agents-md-as-contract —
ai_draft; suggested action: add acceptance criteria and a stopping point to one recurring non-trivial agent request. - harness-engineering/multi-agent-coordination-patterns —
ai_draft; suggested action: define repo ownership and rollback responsibility before any cross-repo delegation test. - ai-ecosystem/hermes-agent —
ai_draft; suggested action: verify cloud-gateway continuation with one closed-laptop task and one Codex session resume.
[2026-09-06] absorb | AI Briefing 2026-09-06 Morning
Pages touched: ai-ecosystem/openai-codex-superapp, ai-tools/ai-writing-guardrails, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/agent-driven-qa, harness-engineering/model-routing, claude-code/self-improving-skills, product-trends/agent-native-architecture, forecasts/one-person-billion-dollar-company Key additions: Astra execution surfaces, evidence-gated self-healing and cleanup, Computer Use QA, task-level model routing, concrete writing deletion rules, skill context-cost checks, enterprise process redesign, and vibe manufacturing as a hypothesis. Files processed:
- AI Briefing 2026-09-06 Morning -> absorbed / absorb_now
Ordinary model announcements, launch promotion, and one-off product reactions remain raw-only.
Pending Jean review
- ai-ecosystem/openai-codex-superapp -
ai_draft; measure one end-to-end Astra task from intent to accepted result. - ai-tools/ai-writing-guardrails -
ai_draft; test the deletion pass on one Chinese draft. - harness-engineering/agent-trust-verification -
ai_draft; add evidence receipts and recovery outcomes to one acceptance checklist. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; add trace, context, effort, cost, and accepted-fix fields to one regression task. - harness-engineering/agent-driven-qa -
ai_draft; measure Computer Use false positives, false negatives, and review time. - harness-engineering/model-routing -
ai_draft; compare fixed-task accepted-result cost across three models. - claude-code/self-improving-skills -
ai_draft; inspect one skill's load cost, trigger rate, and accepted outcomes. - product-trends/agent-native-architecture -
ai_draft; map one workflow's actions, state, permissions, evidence, and recovery. - forecasts/one-person-billion-dollar-company -
ai_draft; keep vibe manufacturing as a hypothesis until real fulfillment evidence exists.
[2026-09-06] absorb | AI Briefing 2026-09-06 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/self-verification-loops, claude-code/self-improving-skills, product-trends/agent-native-architecture Key additions: Follow Builders was skipped as stale; absorbed scarce weekly-model quota routing, Agent Inbox receipt/ablation/black-box verification, method-bearing skill lifecycle, and physical-service / launch-channel agent-native product tests. Files processed:
- AI Briefing 2026-09-06 Afternoon → harness-engineering/model-routing, harness-engineering/self-verification-loops, claude-code/self-improving-skills, product-trends/agent-native-architecture
Pending Jean review
- harness-engineering/model-routing —
ai_draft; suggested action: define one routing table row for scarce weekly-model quota, including when to spend it and when to fall back. - harness-engineering/self-verification-loops —
ai_draft; suggested action: add receipt, identity check, ablation, and black-box behavior fields to one recurring agent workflow. - claude-code/self-improving-skills —
ai_draft; suggested action: classify one skill as generic-process, method-bearing, or safety-boundary before pruning. - product-trends/agent-native-architecture —
ai_draft; suggested action: test one physical-service or launch-channel workflow for evidence, actionability, reviewability, and spam resistance. 2026-09-06 21:30 | EMERGE | raw emergent themes (14d, 64 sources, 10 clusters) | outputs/ideas/2026-09-06-raw-emergent-themes.md
[2026-09-06] absorb | AI Briefing 2026-09-06 Evening
Pages touched: harness-engineering/ai-cost-governance, harness-engineering/model-routing, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, ai-tools/ai-writing-guardrails Key additions: hard model-routing boundaries, task-level trust signals, computer-science requirements for vibe coding, no-edit goal recovery before refactoring, and separate capability versus human-voice checks for writing models. Files processed:
- AI Briefing 2026-09-06 Evening -> harness-engineering/model-routing, harness-engineering/ai-cost-governance, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, ai-tools/ai-writing-guardrails
Ordinary product announcements, one-off demos, and low-information reactions remain raw-only.
Pending Jean review
- harness-engineering/ai-cost-governance -
ai_draft; suggested action: test one hard routing boundary against prompt-only guidance and record accepted result, latency, tokens, retries, and rework. - harness-engineering/model-routing -
ai_draft; suggested action: add one route for routine code and one fallback route for novel reasoning, then compare task-level outcomes. - harness-engineering/agentic-software-is-systems-engineering -
ai_draft; suggested action: locate the original vibe-coding study before using its predictor claims in a training or hiring decision. - harness-engineering/self-verification-loops -
ai_draft; suggested action: add a no-edit goal-recovery stage before one recurring refactor task and record rejected, accepted, and unverified suggestions. - ai-tools/ai-writing-guardrails -
ai_draft; suggested action: run a blind comparison on one Chinese draft and score factuality, authorial voice, edit distance, and detected AI markers separately.
[2026-09-06] absorb | A Split Verdict on Fable vs. Astra
Pages touched: product-trends/delegate-vs-sit-beside, harness-engineering/ai-cost-governance, writing/writing-with-ai Key additions: task-fit evidence for delegated versus in-loop model work, execution bounds for token-efficient agents, and persistent-context rules for Compound Writing. Files processed:
- Every — A Split Verdict on Fable vs. Astra -> product-trends/delegate-vs-sit-beside, harness-engineering/ai-cost-governance, writing/writing-with-ai
Pending Jean review
- product-trends/delegate-vs-sit-beside —
ai_draft; suggested action: compare one delegated and one in-loop task using accepted result, rework, and model cost. - harness-engineering/ai-cost-governance —
ai_draft; suggested action: record effort, tool count, hard-limit compliance, accepted result, and rework for one recurring workflow. - writing/writing-with-ai —
ai_draft; suggested action: test whether persistent voice and editorial files improve the next Chinese draft without over-templating it.
[2026-09-07] absorb | AI Briefing 2026-09-07 Morning
Pages touched: harness-engineering/model-routing, harness-engineering/advisor-pattern, claude-code/context-window-optimization, harness-engineering/agent-driven-qa, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture, harness-engineering/ai-security-speed-mismatch Key additions: effort and accepted-task cost routing, read-only advisor context boundaries, evidence-rich AI PR review, page-local WebMCP capability surfaces, and hidden-reasoning observability limits. Files processed:
- AI Briefing 2026-09-07 Morning -> absorbed / absorb_now
Ordinary model announcements, promotions, duplicate timeline items, and one-off reactions remain raw-only.
Pending Jean review
- harness-engineering/model-routing -
ai_draft; suggested action: compare low, medium, and high effort on one fixed task set with accepted result, cost, latency, and rework. - harness-engineering/advisor-pattern -
ai_draft; suggested action: run one complex task with an explicit read-only advisor and compare accepted result, rework, and cost. - claude-code/context-window-optimization -
ai_draft; suggested action: compare full-history and fresh-context delegation on one task and record model selection, context size, and accepted result. - harness-engineering/agent-driven-qa -
ai_draft; suggested action: add pseudocode, diagram, test receipt, and optional browser evidence to one agent-authored PR. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: extend one routing ledger with intelligence-per-dollar proxy, accepted result, retries, latency, and rework. - product-trends/agent-native-architecture -
ai_draft; suggested action: prototype one page-local diagnostic tool with explicit discovery, authorization, evidence, and recovery behavior. - harness-engineering/ai-security-speed-mismatch -
ai_draft; suggested action: define one black-box monitoring receipt for a high-capability model and verify incident reconstruction.
[2026-09-07] absorb | AI Briefing 2026-09-07 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, product-trends/agent-native-architecture, product-trends/software-soul-ai-slop Key additions: Added afternoon evidence about benchmark freshness, browser-agent isolation, review artifacts, enterprise agent data boundaries, and focus/measurement controls for AI slop. Files processed:
- AI Briefing 2026-09-07 Afternoon -> harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, product-trends/agent-native-architecture, product-trends/software-soul-ai-slop
- AI Builders Digest 2026-09-07 -> skipped_duplicate / raw_only; merged into afternoon briefing.
Pending Jean review
- harness-engineering/model-routing —
ai_draft; suggested action: add benchmark freshness, local task result, accepted-output cost, and provider fallback to one routing table row. - harness-engineering/agent-trust-verification —
ai_draft; suggested action: define a browser-agent checklist covering isolated session, credential scope, review evidence, allowed probes, and reporting language. - harness-engineering/self-verification-loops —
ai_draft; suggested action: add one review-evidence bundle and one order-swap consistency check to a small local eval. - product-trends/agent-native-architecture —
ai_draft; suggested action: map one browser-agent workflow across identity, data access, session isolation, evidence, and human handoff. - product-trends/software-soul-ai-slop —
ai_draft; suggested action: define one local writing task where focus, human taste, and blind comparison all matter.
[2026-09-07] absorb | AI Briefing 2026-09-07 Evening
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-cost-governance, harness-engineering/multi-agent-coordination-patterns, product-trends/agent-native-architecture, product-trends/software-soul-ai-slop, ai-tools/ai-writing-guardrails Key additions: role-based model routing, review evidence, bounded evaluation, agent-native workflow surfaces, task-level cost accounting, and deletion rules were integrated; ordinary announcements remain raw-only. Files processed:
- AI Briefing 2026-09-07 Evening → harness-engineering/model-routing and related pages
Pending Jean review: updated pages remain
ai_draft; verify fixed-task routing, evidence bundles, and writing deletion rules.
[2026-09-08] absorb | AI Briefing 2026-09-08 Morning
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-driven-qa, product-trends/agent-native-architecture, harness-engineering/ai-cost-governance
Key additions: usage visibility and effort as routing inputs; explicit worker deliverables and independent review for multi-agent coordination; blast-radius based PR review; agent-native platform and credential boundaries; task-level quota and accepted-cost accounting.
Files processed:
- AI Briefing 2026-09-08 Morning → existing concept pages above
Pending Jean review:
ai_draftupdates need fixed-task checks for effort, skill triggering, accepted result, cost, latency, rework, and human review burden.
[2026-09-08] absorb correction | AI Briefing 2026-09-08 Morning
The raw briefing was reprocessed after removing one duplicate source URL. No additional Wiki page changes were needed; the five existing concept updates remain the durable absorb result.
Files processed:
[2026-09-08] absorb | AI Briefing 2026-09-08 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, product-trends/agent-native-architecture, harness-engineering/self-evolving-harness-composability
Key additions: task saturation and hard routing boundaries; blind worker evals for agent-friendly codebases; local-computer agent surfaces; prewritten skill scripts as a conservative self-evolution path.
Files processed:
- AI Briefing 2026-09-08 Afternoon -> existing concept pages above
- AI Builders Digest 2026-09-08 -> skipped_duplicate / raw_only; merged into afternoon briefing.
Pending Jean review:
- harness-engineering/model-routing —
ai_draft; suggested action: define one routine-read route and one frontier-reasoning route, then compare accepted-result cost and rework. - harness-engineering/multi-agent-coordination-patterns —
ai_draft; suggested action: test one AGENTS.md or skill change with blind worker runs and a fixed result rubric. - product-trends/agent-native-architecture —
ai_draft; suggested action: map one local-computer workflow across identity, files, app access, task history, evidence, and rollback. - harness-engineering/self-evolving-harness-composability —
ai_draft; suggested action: identify one repeated ad hoc automation script and decide whether it should become a skill script.
[2026-09-08] absorb | AI Briefing 2026-09-08 Evening
Pages touched: harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/loop-engineering, ai-tools/ai-writing-guardrails, harness-engineering/prompt-caching, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture, claude-code/overview
Key additions: task-level model routing and cost evidence; review artifacts and execution boundaries; feedback infrastructure for knowledge work; nested growth loops; writing deletion checks; experimental subagent caching; and capability-plus-boundary requirements for local Agent products.
Files processed:
- AI Briefing 2026-09-08 Evening → existing concept and overview pages above
Raw-only material:
- Product announcements, ordinary tool mentions, one-off promotions, and unsupported personal claims stayed in raw and did not create standalone pages.
- No additional files were in scope for this single-file absorb.
Pending Jean review:
- harness-engineering/model-routing —
ai_draft; compare routine and optimization routes on a fixed task set. - harness-engineering/agent-trust-verification —
ai_draft; add evidence, blast-radius, credential, isolation, and rollback fields to one evaluation. - harness-engineering/agentic-software-is-systems-engineering —
ai_draft; compare coding and knowledge workflows by feedback infrastructure. - harness-engineering/loop-engineering —
ai_draft; run one small loop with artifact, acceptance, external feedback, and next-cycle record. - ai-tools/ai-writing-guardrails —
ai_draft; blind-test deletion rules for factuality, qualifiers, density, and voice. - harness-engineering/prompt-caching —
ai_draft; test resumed subagent caching against a no-cache baseline. - harness-engineering/ai-cost-governance —
ai_draft; extend one task ledger with quota, bill, accepted result, retries, latency, and review cost. - product-trends/agent-native-architecture —
ai_draft; map a local-agent workflow across capability, identity, runtime, evidence, handoff, and rollback. - claude-code/overview —
ai_draft; run prompt-audit in a disposable worktree and verify with a regression task.
[2026-09-08] absorb correction | AI Briefing 2026-09-08 Evening
The saved evening report was re-rendered after a final global source-URL uniqueness check. The local MCP comparison remains in the GitHub section only, so the final report has 40 unique source URLs. No additional Wiki page changes were needed; the same nine existing page updates remain valid.
Files processed:
- AI Briefing 2026-09-08 Evening — corrected hash recorded in
wiki/_absorb_log.json
Pending Jean review:
- The nine updated pages remain
ai_draft; see the absorb entry above for the fixed-task verification prompts.
[2026-09-08] absorb | The first GPT-6 model
Pages touched: harness-engineering/model-spikiness, harness-engineering/model-harness-fit, harness-engineering/skills-into-loops, harness-engineering/agent-trust-verification, harness-engineering/ai-cost-governance
Key additions: Ben Tossell's GPT-6 Astra trial adds evidence about model spikiness, harness-dependent evaluation, skill loops, external-action risk, and task-level token accounting.
Files processed:
- Ben's Bites: The first GPT-6 model → existing concept pages above
Pending Jean review
- harness-engineering/model-spikiness —
ai_draft; suggested action: verify Astra stability with a fixed task set. - harness-engineering/model-harness-fit —
ai_draft; suggested action: record harness and state strategy in future model comparisons. - harness-engineering/skills-into-loops —
ai_draft; suggested action: test one local tool from session to skill to repeatable artifact. - harness-engineering/agent-trust-verification —
ai_draft; suggested action: add consent, scope, audit, stop, rollback, and approval fields to one evaluation. - harness-engineering/ai-cost-governance —
ai_draft; suggested action: add exploration budget and accepted residue to one workflow ledger.
[2026-09-09] absorb | last 30 days scan
Pages touched: index, _backlinks Key additions: No new absorbs; 269/269 raw files already in log. Rebuilt index (451 pages) and backlinks — index was stale, now resynced. Files processed: none
[2026-09-09] absorb | AI Briefing 2026-09-09 Morning
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-driven-qa, harness-engineering/ai-security-speed-mismatch, product-trends/agent-native-architecture, ai-tools/ai-writing-guardrails, ai-ecosystem/openai-codex-superapp, ai-ecosystem/hermes-agent, claude-code/overview
Key additions: role-based model routing; planner-worker coordination with durable lessons; blast-radius review and deterministic result checks; prompt-injection evaluation; capability, identity, isolation, memory, and rollback boundaries for agent-native products; cross-model writing guardrails; Codex visual and execution surfaces; Hermes provider integration; and Claude Code plugin and tool-result boundaries.
Files processed:
- AI Briefing 2026-09-09 Morning → existing concept and overview pages above
Raw-only material:
- Product announcements, promotional claims, entertainment discussion, and unsupported personal model rankings stayed in raw and did not create standalone pages.
Pending Jean review:
- The nine updated pages remain
ai_draft; verify fixed-task routing, bounded handoffs, blast-radius classification, prompt-injection receipts, permission and rollback boundaries, writing quality, provider access, and Claude Code release behavior.
[2026-09-09] absorb | AI Briefing 2026-09-09 Afternoon
Pages touched: harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, ai-ecosystem/openai-codex-superapp, harness-engineering/model-routing, ai-ecosystem/ai-inference-rationing-2026
Key additions: prompt-injection scaffolding and public bypass propagation; chat plus computer as product grammar; Astra demand and Images 2.5 as work-surface signals; provider-path and forced-routing inputs; and subscription gating as a visible inference-rationing control.
Files processed:
- AI Briefing 2026-09-09 Afternoon → existing concept pages above
- AI Builders Digest 2026-09-09 → skipped_duplicate / raw_only because it was merged into the afternoon briefing
Raw-only material:
- Entertainment timeline items, sports, ordinary product reactions, and unsupported one-off claims stayed in raw and did not create standalone pages.
Pending Jean review:
- harness-engineering/agent-trust-verification —
ai_draft; add prompt-injection probe evidence, network exception scope, public-write review, and bypass-report handling to one checklist. - product-trends/agent-native-architecture —
ai_draft; map one personal-agent workflow across data sources, form actions, approval, payment scope, evidence, and rollback. - ai-ecosystem/openai-codex-superapp —
ai_draft; test one Astra plus image-generation workflow with quota, asset quality, accepted result, and rollback recorded. - harness-engineering/model-routing —
ai_draft; add provider path, forced-routing behavior, world-knowledge dependency, accepted result, cost, and rework to one routing table row. - ai-ecosystem/ai-inference-rationing-2026 —
ai_draft; track whether capacity pressure appears as rate limits, quota resets, subscription pauses, or degraded task latency.
[2026-09-09] absorb | AI Briefing 2026-09-09 Evening
Pages touched: claude-code/agents-md-as-contract, claude-code/llm-wiki-pattern, harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/model-routing, harness-engineering/ai-security-speed-mismatch, harness-engineering/multi-agent-coordination-patterns, product-trends/agent-native-architecture
Key additions: execution-oriented AGENTS.md rules and prompt audit; parallel LLM Wiki delivery; tool-level trust receipts; provider and region-aware routing; prompt-injection propagation; bounded worker coordination; and context, permission, evidence, and rollback requirements for agent-native products.
Files processed:
- AI Briefing 2026-09-09 Evening → existing concept pages above
Raw-only material:
- Product announcements, promotions, entertainment discussion, unsupported scientific or model claims, and ordinary reactions stayed in raw and did not create standalone pages.
Pending Jean review:
- The eight updated pages remain ai_draft; verify prompt-audit changes, multi-agent review evidence, provider and residency routing, prompt-injection receipts, worker bounds, and agent-native permission and rollback boundaries.
[2026-09-09] absorb | Better design than Fable
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/ai-cost-governance, harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, harness-engineering/agentic-infrastructure
Key additions: Cursor 的 planner/worker SQLite 实验、Ramp Router 的任务级路由、Kimi K3 的 token 经济学、共享工作面、OpenShip 部署控制面与 agent 外部行动边界被合并到既有主题页。
Files processed:
- Ben's Bites — Better design than Fable → existing wiki pages; no standalone newsletter page
[2026-09-10] absorb | AI Briefing 2026-09-10 Morning
Pages touched: harness-engineering/ai-security-speed-mismatch, harness-engineering/agent-driven-qa, harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-trust-verification, claude-code/llm-wiki-pattern, claude-code/agents-md-as-contract, claude-code/context-window-optimization, claude-code/overview, product-trends/agent-native-architecture
Key additions: Defense Factory 的分阶段安全验证、提示注入与 Agent Wiki 传播边界、Astra/Luna/Sol 角色路由、共享 LLM Wiki 与项目上下文结构、Claude Code 2.1.267 的 prompt 与恢复控制,以及 prompt-built Dashboard 的 agent-native 工作面。
Files processed:
- AI Briefing 2026-09-10 Morning → existing concept and overview pages above
Raw-only material:
- 实验室离职与安全动机争论、模型价格和速度体验、产品预告、移动端需求、娱乐/体育/品牌宣传和缺少细节的短反应留在 raw,未创建 standalone wiki page。
Pending Jean review:
- 上述更新页面中的 AI-authored 判断仍为
ai_draft;优先验证提示注入/Agent Wiki 事件、2.1.267 行为、路由成本基线和共享上下文的实际返工变化。
[2026-09-10] absorb | AI Briefing 2026-09-10 Evening
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/model-routing, harness-engineering/ai-cost-governance
Key additions: the briefing added source-grounded notes on external enforcement for agent permissions, strategic review and learning gaps, role-based model routing, and task-level cost accounting.
Files processed:
- AI Briefing 2026-09-10 Evening → harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/model-routing, harness-engineering/ai-cost-governance
Ordinary model announcements, product announcements, and one-off timeline reactions remain source-only in raw/. All four touched pages retain knowledge_status: ai_draft and a Pending Jean review item.
[2026-09-10] absorb | Everyone needs a Muse. Pages touched: harness-engineering/agent-trust-verification, harness-engineering/ai-security-speed-mismatch, harness-engineering/multi-agent-coordination-patterns, harness-engineering/self-verification-loops, product-trends/agent-native-architecture. Key additions: Muse approval and audit boundaries, Anthropic long-trajectory safety evidence, OpenAI multi-agent research and Lean verification, and reusable design context. File: Ben's Bites — Everyone needs a Muse. No standalone newsletter wiki page created. Updated pages remain ai_draft and include Pending Jean review.
[2026-09-10] absorb | AI Briefing 2026-09-10 午间
Pages touched: claude-code/llm-wiki-pattern, harness-engineering/better-code-more-slowly, claude-code/context-window-optimization, harness-engineering/zero-trust-ai-agents, product-trends/design-is-understanding-not-output, ai-ecosystem/deepseek-v4
Key additions: Matt Pocock 摩擦消失掩盖战略性错误与 dotey 三步 agent review 提示词并入 better-code-more-slowly;MCP alwaysLoad 上下文成本并入 context-window-optimization;MCP 读取/执行边界与 agent 写入内容按不可信输入处理并入 zero-trust-ai-agents;Kami 文档排版服务理解并入 design-is-understanding-not-output;V4.1 Flash 发布记入 deepseek-v4 实体页;交付物 Wiki 材料补第二条出处。
Files processed:
- AI Briefing 2026-09-10 午间 → 上述六个既有页面
Raw-only material:
- 实验室离职与安全动机争论(早间已留 raw)、DeepSeek 架构观察、builder 动态(产品发布、定价、人事、娱乐回应)留在 raw,未创建 standalone wiki page。
Idea candidates(进入 emergence 队列,待跨源确认):
- AI 对 GDP 影响慢于能力曲线:Levie 企业物理定律 vs Shipper 自动化创造工作(tension pair)
- AI 叙事三分裂(能力突破 / 存在风险 / 渐进迭代)
- 机器人纠错数据:验证过的短纠错片段成功率 48.3% > 完整模仿 36.7%(弱源,👍2)
- Vibe coding 把编程门槛变成表达门槛
[2026-09-10] absorb | AI Builders Digest 2026-09-10
Files processed:
- AI Builders Digest 2026-09-10 → skipped_duplicate;Builder 动态与 AI Briefing 2026-09-10 午间完全重叠,无独立新内容
Pending Jean review:
- 本次更新的六个页面中 AI-authored 判断仍为
ai_draft;better-code-more-slowly 升级为 2 sources 但仍需 Jean 确认是否 mark mature。
[2026-09-11] absorb | 30-day scan (no-op)
- Scanned 279 raw files modified in last 30 days (briefings, newsletters, to-learn 跨国串门儿计划 episodes, briefing test files).
- All 279 already in
_absorb_log.jsonwith matching SHA256 → 0 files to process, 0 hash changes. - Ran
rebuild_indexes.pyper skill protocol, then reverted: the script dropped curated index sections (MOC Pages / Recently Updated / Pages Needing Jean Review) and churned_backlinks.json(~12k lines) on a no-op run. Restored both files from git HEAD since no wiki pages changed. - Flagged for fix:
rebuild_indexes.pyshould preserve curated sections inindex.mdand be diff-stable on no-op runs. - No wiki pages created or updated; no new Pending Jean review items from this run.
[2026-09-11] absorb | AI Briefing 2026-09-11 Morning
Pages touched: harness-engineering/ai-security-speed-mismatch, ai-ecosystem/deepseek-v4, product-trends/agent-native-architecture, claude-code/context-window-optimization, harness-engineering/ai-cost-governance, claude-code/overview Key additions: Added novel security, model-efficiency, deterministic-agent, context-audit, cost-boundary, and Claude Code runtime signals; repeated prior-day sources remained raw-only. Files processed:
- AI Briefing 2026-09-11 Morning → targeted absorb; ordinary announcements and low-detail observations retained in raw.
[2026-09-11] absorb | AI Briefing 2026-09-11 Afternoon 17-43
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/model-routing, product-trends/agent-native-architecture, harness-engineering/agent-memory-vs-context-substrate, product-trends/design-is-understanding-not-output Key additions: Added model provenance/user-data routing trust boundary; cost/access/provenance model-routing record requirements; agent runtime platform primitives; markdown second-brain context substrate; and deletion-based document layout validation. Files processed:
- AI Briefing 2026-09-11 Afternoon -> absorbed / absorb_now
- AI Builders Digest 2026-09-11 -> skipped_duplicate / raw_only; merged into afternoon briefing Pending Jean review:
- harness-engineering/agent-trust-verification: ai_draft; suggested action: verify Anthropic routing/distillation claims against provider logs or independent analysis before using them as vendor judgment.
- harness-engineering/model-routing: ai_draft; suggested action: add provider path, disclosure state, data-retention mode, accepted result, total cost, latency, and rework to one local routing record.
- product-trends/agent-native-architecture: ai_draft; suggested action: compare one cloud-agent workflow and one local-agent workflow on state visibility, permissions, runtime cost, and recovery.
- harness-engineering/agent-memory-vs-context-substrate: ai_draft; suggested action: test one markdown memory folder with claim-status tags and a deletion/review routine.
- product-trends/design-is-understanding-not-output: ai_draft; suggested action: apply deletion validation to one generated report or dashboard artifact.
[2026-09-11] absorb | AI Briefing 2026-09-11 Evening (23-15)
Pages touched: ai-ecosystem/ai-inference-rationing-2026, claude-code/self-improving-skills, harness-engineering/agent-driven-qa
Key additions: OpenAI 暂停 $200 Pro 新订阅(Astra 容量紧张)作为推理配给的首个旗舰级消费证据,新建 mature 概念页 ai-inference-rationing-2026(5 sources);Hamel Husain《The Revenge of the Data Scientist》与 OpenAI Agents API "AWS 时刻" 并入 self-improving-skills;bcherny 的 Anthropic 生产代码护栏清单(每日 Claude fuzzer、自动安全审查、升级路径)并入 agent-driven-qa(升至 7 sources,仍 candidate)。
Files processed:
- AI Briefing 2026-09-11 Evening → absorbed / absorb_now
Pending Jean review:
- ai-ecosystem/ai-inference-rationing-2026 —
ai_draft; suggested action: verify OpenAI Pro pause 是否为临时容量措施还是结构性配给起点,再决定是否升级判断。 - harness-engineering/agent-driven-qa —
ai_draft; suggested action: 把 bcherny 护栏清单裁剪出个人项目版本(lint + 每日 fuzzer 的最小可行组合)。
2026-09-12 00:58 | EMERGE | raw emergent themes | outputs/ideas/2026-09-12-raw-emergent-themes.md
[2026-09-12] absorb | AI Briefing 2026-09-12 Morning
Pages touched: ai-ecosystem/agent-infrastructure-trends, ai-ecosystem/openai-codex-superapp, ai-ecosystem/ai-inference-rationing-2026, ai-tools/overview, claude-code/agents-md-as-contract, claude-code/self-improving-skills, harness-engineering/agent-driven-qa, harness-engineering/ai-security-speed-mismatch, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-cost-governance
Key additions: Added agent infrastructure, Codex boundary, model-cost, Skills evaluation, Agent QA, security-control, and vertical workflow evidence to existing pages. Ordinary announcements, entertainment, promotions, and the unverified privacy claim remained raw-only.
Files processed:
- AI Briefing 2026-09-12 Morning -> absorbed / absorb_now
Pending Jean review:
- ai-ecosystem/agent-infrastructure-trends: ai_draft; suggested action: map one vertical workflow's runtime, identity, approvals, legacy data, and accepted-result evidence.
- ai-ecosystem/openai-codex-superapp: ai_draft; suggested action: verify one Codex cross-surface task from intent through accepted result.
- ai-ecosystem/ai-inference-rationing-2026: ai_draft; suggested action: reproduce the cost-quality comparison on 5-10 recurring tasks with cache and retry data.
- claude-code/agents-md-as-contract: ai_draft; suggested action: audit one project guidance set before editing and compare rework and premature confirmations.
- claude-code/self-improving-skills: ai_draft; suggested action: compare real-trace labels, precision, rework, and accepted results before and after one Skill change.
- harness-engineering/agent-driven-qa: ai_draft; suggested action: add a no-plugin baseline and real-trace annotation pass to one recurring automation.
- harness-engineering/ai-security-speed-mismatch: ai_draft; suggested action: map one workflow's identity, network, tool, incident, and independent-review controls.
- harness-engineering/agentic-software-is-systems-engineering: ai_draft; suggested action: map one vertical workflow from intent and permissions through recovery and acceptance.
- harness-engineering/ai-cost-governance: ai_draft; suggested action: record cache reads, retries, runtime, spend, and accepted results across two routed models.
[2026-09-12] re-absorb | AI Briefing 2026-09-12 Morning
Pages touched: existing 10 pages re-read; no additional wiki changes.
Key additions: Reprocessed the briefing after removing one duplicate GPT-Rosalind source URL from the rendered report. The final raw hash is sha256:a10eb425c25bb1f27b07a43aacb3b4541a800a47721edf9f7e7c57a681744d21.
Files processed:
- AI Briefing 2026-09-12 Morning -> absorbed / absorb_now
[2026-09-12] absorb | AI Briefing 2026-09-12 Evening
Pages touched: claude-code/agents-md-as-contract, harness-engineering/self-verification-loops, harness-engineering/model-routing, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-cost-governance, harness-engineering/agent-trust-verification, product-trends/agent-native-architecture
Key additions: Absorbed the evening timeline's reusable signals on specific Agent contracts, evidence-preserving verification, provider/cache-aware routing, Agent-assisted rewrites, task-level cost governance, independent evaluation, and domain-shaped Agent products. Ordinary announcements, entertainment, promotions, and unverified claims remained raw-only.
Files processed:
- AI Briefing 2026-09-12 Evening -> absorbed / absorb_now
Pending Jean review:
- claude-code/agents-md-as-contract:
ai_draft; suggested action: run a read-only audit on one project and compare rule coverage, context cost, rework, and premature stops. - harness-engineering/self-verification-loops:
ai_draft; suggested action: compare filtered tool output with the full log and record missed failures and accepted results. - harness-engineering/model-routing:
ai_draft; suggested action: compare a native endpoint and an aggregator on one fixed task with cache, cost, latency, and rework. - harness-engineering/agentic-software-is-systems-engineering:
ai_draft; suggested action: map one service migration by seam, compatibility tests, traffic evidence, rollback, and accepted result. - harness-engineering/ai-cost-governance:
ai_draft; suggested action: check the actual Claude Code allowance on September 14 and compare one recurring task before and after. - harness-engineering/agent-trust-verification:
ai_draft; suggested action: define the minimum independent-evaluator receipt for one high-risk local Agent task. - product-trends/agent-native-architecture:
ai_draft; suggested action: define one bounded AI employee role with a job, skills, manager, budget, permissions, and accepted result.
[2026-09-12] absorb | Every - What I Learn When I Run Out of AI
Pages touched: ai-ecosystem/ai-inference-rationing-2026, harness-engineering/ai-cost-governance Key additions: Added first-person evidence that inference quotas can create a cognitive cooling interval, and extended cost governance with fast/deep/wait routing plus post-wait cancellation, scope change, delay, and accepted-result fields. Files processed:
- Every - What I Learn When I Run Out of AI -> absorbed / absorb_now Pending Jean review:
- ai-ecosystem/ai-inference-rationing-2026 -
ai_draft; suggested action: measure 5-10 repeated tasks for quota, wait time, cancellation or scope change, retries, and accepted result. - harness-engineering/ai-cost-governance -
ai_draft; suggested action: addwait_reason, post-cooling state, delay, token, rework, and accepted result to one recurring task ledger.
[2026-09-13] absorb | AI Briefing 2026-09-13 Morning
Pages touched: harness-engineering/ai-security-speed-mismatch, harness-engineering/agent-driven-qa, harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agentic-software-is-systems-engineering, claude-code/overview, ai-ecosystem/openai-codex-superapp, harness-engineering/browser-harness, product-trends/agent-native-architecture, harness-engineering/ai-cost-governance
Key additions: Absorbed reusable signals on independent evaluation, evaluator-gaming risk, asynchronous planner-worker coordination, multi-model instruction audits, language-agnostic Agent engineering, Claude Code 2.1.270, local Codex execution, browser capability surfaces, pre-coding clarification, and contact-sheet cost controls. Ordinary announcements, ads, entertainment, bare links, and unverified privacy or incident claims remained raw-only.
Files processed:
- AI Briefing 2026-09-13 Morning -> absorbed / absorb_now
Pending Jean review:
- harness-engineering/ai-security-speed-mismatch:
ai_draft; verify the cited incident and map evaluator authority, evidence preservation, scoring isolation, and release gates. - harness-engineering/agent-driven-qa:
ai_draft; add evaluator-gaming, evidence-preservation, independent replay, and deterministic checks to one bounded security regression. - harness-engineering/model-routing:
ai_draft; benchmark planner-worker routing against polling and single-model baselines. - harness-engineering/multi-agent-coordination-patterns:
ai_draft; record completion, timeout, failure, accepted-result, and shared-state evidence. - harness-engineering/agentic-software-is-systems-engineering:
ai_draft; compare cross-language implementation with language-independent tests, performance, security, and rollback evidence. - claude-code/overview:
ai_draft; verify the installed version and disposable-project behavior for read-only Git, inline Bash, delegation, and approvals. - ai-ecosystem/openai-codex-superapp:
ai_draft; test a read-only cross-surface task on a disposable account with permission, token, recovery, and accepted-result evidence. - harness-engineering/browser-harness:
ai_draft; compare read-only and form tasks with action receipts, permission prompts, recovery, and replay evidence. - product-trends/agent-native-architecture:
ai_draft; add a clarification checkpoint and record ambiguity, scope, UX/DX/AX tradeoff, and rework. - harness-engineering/ai-cost-governance:
ai_draft; compare per-image review with contact-sheet review using calls, token use, missed defects, rework, and accepted result.
[2026-09-13] absorb | AI Briefing 2026-09-13 Afternoon
Pages touched: harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, harness-engineering/model-routing, claude-code/agents-md-as-contract Key additions: Added browser-agent action validation and embedded-evaluator trust boundaries; system-of-record-as-domain-harness product framing; real-repo bug evals as model-routing input; and skill trigger/done definitions as AGENTS.md contract hygiene. Files processed:
- AI Briefing 2026-09-13 Afternoon → harness-engineering/agent-trust-verification, product-trends/agent-native-architecture, harness-engineering/model-routing, claude-code/agents-md-as-contract
- AI Builders Digest 2026-09-13 → skipped duplicate / raw only; merged into the afternoon briefing.
Pending Jean review:
- harness-engineering/agent-trust-verification —
ai_draft; suggested action: verify Claude browser-agent safeguards and ExploitGym details against primary reports before using them as hard policy. - product-trends/agent-native-architecture —
ai_draft; suggested action: define one system-of-record workflow as a domain harness candidate. - harness-engineering/model-routing —
ai_draft; suggested action: record harness/prompt-contract version and irrelevant-bug rate in one local routing eval. - claude-code/agents-md-as-contract —
ai_draft; suggested action: audit one skill trigger and done definition against real tasks.
[2026-09-13] absorb | AI Briefing 2026-09-13 Evening
Pages touched: harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, harness-engineering/ai-engineering-culture-stack, harness-engineering/model-routing, harness-engineering/matt-pocock-ai-coding-workflow, product-trends/agent-native-architecture Key additions: Added the shift from generation speed to acceptance responsibility, review-throughput limits for parallel agents, AI Engineering product judgment, execution and commit boundaries for routing, and bounded AI employee work as an agent-native product unit. Files processed:
- AI Briefing 2026-09-13 Evening → six existing pages; no new page created.
Pending Jean review:
- harness-engineering/agentic-software-is-systems-engineering —
ai_draft; suggested action: define one task's problem statement, commit boundary, acceptance evidence, hardening time, and accountable owner. - harness-engineering/self-verification-loops —
ai_draft; suggested action: compare sequential and parallel routes by review queue, missed failures, rework, and accepted-result evidence. - harness-engineering/ai-engineering-culture-stack —
human_verifiedpage with AI-draft addendum; suggested action: test one build-loop record for product decision, user evidence, risk, budget, and accepted result. - harness-engineering/model-routing —
ai_draft; suggested action: record execution location, role, latency target, commit event, accepted result, cost, and rework. - harness-engineering/matt-pocock-ai-coding-workflow —
ai_draft; suggested action: test the prototype → spec → tickets → implementation chain on one disposable repository. - product-trends/agent-native-architecture —
ai_draft; suggested action: define one bounded AI employee role with state, permissions, escalation, budget, rollback, and accepted result.
[2026-09-13] absorb | What to Make of the Anthropic Warning
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/ai-security-speed-mismatch, harness-engineering/self-verification-loops Key additions: Every's personal benchmarks, embedded evaluator proposal, capability pacing, and cooling checkpoints were integrated into existing pages; vendor claims remain attributed and bounded. Files processed:
- What to Make of the Anthropic Warning → existing verification and safety concepts.
[2026-09-14] absorb | AI Briefing 2026-09-14 Morning
Pages touched: harness-engineering/agentic-software-is-systems-engineering, harness-engineering/model-routing, harness-engineering/self-verification-loops, harness-engineering/ai-cost-governance, harness-engineering/ai-security-speed-mismatch, ai-ecosystem/model-sovereignty-risk, ai-ecosystem/hermes-agent, product-trends/agent-native-architecture Key additions: The Twitter-only briefing added attributed evidence about agent execution loops, routing parameters, verification, visual-input cost, defensive coverage, local-model continuity, Hermes controls, and agent-native product boundaries; ordinary promotions and unverified claims remained raw-only. Files processed:
- AI Briefing 2026-09-14 Morning → selected existing concept pages.
Absorb state:
absorbed/absorb_now; hashsha256:acfafde6a810486aa4803734f082aeee9e55af7f9373f68fb0015f3ddf24c3b5.
Pending Jean review:
- harness-engineering/agentic-software-is-systems-engineering —
ai_draft; suggested action: test one bounded incident workflow with human approval and accepted-result evidence. - harness-engineering/model-routing —
ai_draft; suggested action: record model role, location, reasoning setting, cost, latency, and rework for one task. - harness-engineering/self-verification-loops —
ai_draft; suggested action: compare intermediate checks and post-release observation against accepted results. - harness-engineering/ai-cost-governance —
ai_draft; suggested action: benchmark contact-sheet and single-image review with missed defects and rework. - harness-engineering/ai-security-speed-mismatch —
ai_draft; suggested action: map one critical workflow to defensive coverage and rollback evidence. - ai-ecosystem/model-sovereignty-risk —
ai_draft; suggested action: test one documented local-model fallback end to end. - ai-ecosystem/hermes-agent —
ai_draft; suggested action: verify auxiliary-model routing and reasoning controls on one real task. - product-trends/agent-native-architecture —
ai_draft; suggested action: define one agent-native workflow with consent, action scope, pause, and recovery controls.
[2026-09-14] absorb | AI Briefing 2026-09-14 Afternoon
Pages touched: harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering Key additions: Added routing variance, lazy skill loading, sandbox configuration, and hardening-time rules from the afternoon briefing. Files processed:
- AI Briefing 2026-09-14 Afternoon → harness-engineering/model-routing, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering
- AI Builders Digest 2026-09-14 → skipped_duplicate / raw_only because it was merged into the afternoon briefing
Pending Jean review
- harness-engineering/model-routing —
ai_draft; suggested action: add variance, retry count, subagent role, unit cost, accepted result, and rework to one local routing ledger. - harness-engineering/multi-agent-coordination-patterns —
ai_draft; suggested action: test one skill-routing task with metadata, loaded skill version, context tokens, accepted result, and retry count recorded. - harness-engineering/agent-trust-verification —
ai_draft; suggested action: document sandbox config, approval gates, evidence path, and hardening time for one high-risk local agent task. - harness-engineering/agentic-software-is-systems-engineering —
ai_draft; suggested action: add hardening time, live walkthrough, accepted-result evidence, and rollback path to one active agent workflow.
[2026-09-14] absorb | AI Briefing 2026-09-14 Evening
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/google-agent-skill-patterns, harness-engineering/agent-harness-worker-model, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/matt-pocock-ai-coding-workflow, ai-ecosystem/ai-chip-architecture
Key additions: evaluator-aware verification, explicit hardening phases, lazy MCP Skill loading, composable Harness jobs, software-factory design, and full-stack AI Infra mapping were integrated into existing pages; ordinary briefing items remained raw-only.
Files processed:
- AI Briefing 2026-09-14 Evening → existing concept pages above
Decision: absorbed / absorb_now; raw hash sha256:eebd9103e5373ebd8de01bc2e3dd41d5ad9a6d918ec9cc65b05497144b669969.
Pending Jean review: all seven touched pages remain ai_draft; verify or downgrade the new claims against primary sources and local workflow evidence.
[2026-09-15] absorb | AI Briefing 2026-09-15 Morning
Pages touched: claude-code/overview, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/self-verification-loops, harness-engineering/ai-cost-governance, product-trends/agent-native-architecture, ai-ecosystem/agent-infrastructure-trends Key additions: selected reusable patterns from the Twitter-only briefing; duplicate AI Infra coverage and one-off news remained raw-only. Files processed:
- AI Briefing 2026-09-15 Morning → existing concept and overview pages
Pending Jean review
- Existing pages remain
ai_draft; verify runtime controls, test-impact analysis, and one bounded agent-native workflow before treating the additions as confirmed.
[2026-09-15] absorb | AI Briefing 2026-09-15 Afternoon
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/model-routing
Key additions: verification bottlenecks after vibe coding, delegated worktree lifecycle cleanup, Anthropic containment and managed-agent boundaries, artifacts as shared evidence, and effort/subagent-model routing parameters were integrated into existing harness pages.
Files processed:
- AI Briefing 2026-09-15 Afternoon → existing harness-engineering concept pages.
- AI Builders Digest 2026-09-15 → skipped_duplicate / raw_only because it was merged into the afternoon briefing.
Decision: absorbed / absorb_now; raw hash sha256:7d8d3aea937f959ee332f5188192a1e5881c6c957210cb817e79fc395dc004b8.
Pending Jean review: touched pages remain ai_draft; verify one local workflow against accepted-result evidence, worktree lifecycle cleanup, containment boundaries, and routing ledger fields.
[2026-09-16] absorb | AI Briefing 2026-09-16 Evening
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/model-routing, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-cost-governance, harness-engineering/browser-harness, harness-engineering/computer-use-best-practices, harness-engineering/realtime-voice-agent-systems, ai-ecosystem/periodic-labs-ai-for-atoms, product-trends/agent-native-architecture
Key additions: correction-follow-through, validation capacity, effort-aware routing, permission-preserving browser fallback, background Agent delivery, voice-first work entry, and private scientific data were integrated into existing pages; ordinary announcements, promotions, and unverified signals remained raw-only.
Files processed:
- AI Briefing 2026-09-16 Evening → existing concept pages above
Decision: absorbed / absorb_now; raw hash sha256:0ff0d242b3211e8e5e756b9e212e509ca46adfddd7c96d9bf548f977820f4e2e.
Pending Jean review: all ten touched pages remain ai_draft; verify product claims and one local workflow for correction, permissions, accepted results, and task-level cost.
[2026-09-16] absorb | AI Briefing 2026-09-16 Morning
Pages touched: ai-ecosystem/model-labs-becoming-agent-labs, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/multi-agent-coordination-patterns, harness-engineering/agent-trust-verification, harness-engineering/ai-security-speed-mismatch, harness-engineering/model-routing, claude-code/overview, ai-ecosystem/hermes-agent Key additions: Labs maturity boundaries, applied-AI and FDE systems framing, multi-agent review budgets, probability judges, secure-agent boundaries, model-role routing, deferred Skills, and Hermes scale signals were integrated into existing pages; ordinary announcements, promotions, and unverified claims remained raw-only. Files processed:
- AI Briefing 2026-09-16 Morning → existing concept and overview pages above
Decision: absorbed / absorb_now; raw hash sha256:39ad6e5c7b9e72c39680247dd233a3762880be9fe7f57e13ffe2ff0408830aac; final report correction removed one duplicate source URL before save; no additional page changes were needed.
Pending Jean review: all eight touched pages remain ai_draft or equivalent; verify primary sources and one bounded local workflow before treating the new claims as confirmed.
[2026-09-17] absorb | AI Briefing 2026-09-17 Afternoon
Pages touched: harness-engineering/agent-trust-verification, product-trends/cli-as-agent-interface, product-trends/enterprise-workflow-redesign, mental-models/overview
Key additions: Added whiteboard-defense ownership as a trust check, conditional MCP-vs-CLI interface selection, the applied AI layer as workflow redesign, and warranted research as a decision model.
Files processed:
- AI Briefing 2026-09-17 Afternoon → existing concept and overview pages above.
Decision: absorbed / absorb_now; raw hash sha256:bb40d76cf5d1831cd98e58050becc002d3ccb3ea1096262d4e3ad471aed38602. Follow Builders was skipped because the upstream feed had not updated for the local 2026-09-17 slot; ordinary announcements and low-signal timeline items stayed raw-only.
Pending Jean review: touched pages remain ai_draft or equivalent; verify the whiteboard-defense review prompt, MCP-vs-CLI selection rule, enterprise workflow examples, and warranted-research model against future sources or local workflows.
[2026-09-17] absorb | AI Briefing 2026-09-17 Morning
Pages touched: claude-code/overview, ai-ecosystem/model-labs-becoming-agent-labs, harness-engineering/agent-trust-verification, harness-engineering/browser-harness, harness-engineering/model-routing, harness-engineering/agentic-software-is-systems-engineering, claude-code/self-improving-skills, product-trends/cli-as-agent-interface
Key additions: Unified agent surfaces, gated borrowed-browser state, task-shaped CLI/MCP/sandbox selection, separate disclosure and verification layers, skill thinning with deterministic feedback, and small-step scaling for software factories were integrated into existing pages. Hermes, Astra, promotional items, and unverified claims remained raw-only or Pending Jean review.
Files processed:
- AI Briefing 2026-09-17 Morning → existing concept, overview, and product-trend pages above
Decision: absorbed / absorb_now; raw hash sha256:903509e39279e2195921bcce079a503e56c0e67cc4f32ba122a9756e07b95a95.
Pending Jean review: all eight touched pages remain ai_draft or equivalent; verify the product rollout, browser permission scope, routing evidence, deterministic checks, and issue-per-day workflow in primary sources or bounded local tests.
[2026-09-17] absorb | AI Briefing 2026-09-17 Afternoon 22-03
Pages touched: claude-code/claude-cowork-felix-rieseberg, harness-engineering/ai-cost-governance, harness-engineering/dense-feedback-for-agent-debugging, harness-engineering/overview
Key additions: Added first-party evidence that Cowork is now routed inside the main Claude conversation, Databricks' premium-model sub-budget pattern, and a candidate concept for dense local feedback in agent-led systems debugging.
Files processed:
- AI Briefing 2026-09-17 Afternoon → existing Cowork and cost-governance pages, one new candidate concept, and the Harness MOC.
- AI Builders Digest 2026-09-17 →
skipped_duplicate / raw_only; content was merged verbatim into the briefing.
Decision: absorbed / absorb_now; briefing hash sha256:ce62ab5b9915ab437dd8b6d1bb557a6ce9abfc98f7dd676a92bd93a3eac35729; digest hash sha256:ec440ff41248dc1bd479b3699277e58588fe12bcbf2133730d43d229670d5fe5.
Pending Jean review: all touched pages remain ai_draft; keep the dense-feedback page as a candidate until a second source or local implementation confirms it, and verify routing visibility plus model sub-budget outcomes in real use.
[2026-09-17] absorb | AI Briefing 2026-09-17 Evening 22-58
Pages touched: harness-engineering/model-routing, harness-engineering/self-verification-loops, harness-engineering/ai-cost-governance, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/agent-trust-verification, harness-engineering/skill-engineering-as-algorithm, harness-engineering/agent-harness-worker-model, claude-code/overview, ai-ecosystem/hermes-agent, product-trends/agent-native-architecture
Key additions: Integrated multi-layer routing traces, Jev-style judgment evidence, quota handoffs, environment and grader feedback, thinner skills, evidence-first PRs, and agent-native control surfaces into existing pages.
Files processed:
- AI Briefing 2026-09-17 Evening → existing concept, tool, Claude Code, and product-trend pages above
Decision: absorbed / absorb_now; briefing hash sha256:f369208eef26ec881c8d6c73d14484dd5babbc7f202126744bae380d8f3cea18.
Pending Jean review: all ten touched pages remain ai_draft; verify route traces, judgment calibration, quota handoff outcomes, plugin permissions, and evidence-first review behavior in bounded local tests.
[2026-09-17] absorb | Mini-Vibe Check:TypeSafe 的 Jev 在 0.7 秒内评判了我写过的一切
Pages touched: harness-engineering/judgment-engineering, harness-engineering/self-verification-loops, harness-engineering/agent-trust-verification, ai-tools/ai-writing-guardrails Key additions: TypeSafe Jev 的结构化概率判断、过程内验证和个人 benchmark 实践;官方性能主张与小型实验结果保留了证据边界。 Files processed:
Pending Jean review
- harness-engineering/judgment-engineering — ai_draft;验证 Jev 风格原子检查在一个真实重复工作流中的有效性。
- harness-engineering/self-verification-loops — ai_draft;先用人工标签运行 generator-judge 影子循环。
- harness-engineering/agent-trust-verification — ai_draft;验证校准、阈值和动作后证据。
- ai-tools/ai-writing-guardrails — ai_draft;用一组中文样本做人工对照。
[2026-09-18] absorb | AI Briefing 2026-09-18 Morning 08-04
Pages touched: claude-code/overview, ai-ecosystem/model-labs-becoming-agent-labs, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/ai-security-speed-mismatch, harness-engineering/ai-cost-governance, product-trends/cli-as-agent-interface
Key additions: Claude Projects 的项目级并行 Thread 与执行入口产品化、实验室自研与监督指标、聚合结果的 Thread 级证据、软件工厂的小步扩容、窄决策器的安全边界,以及并行额度和隐藏路由的成本账本。Skill 精简、多层路由与普通产品公告因与既有页面重复或证据不足保留 raw-only。
Files processed:
- AI Briefing 2026-09-18 Morning → existing concept, Claude Code, harness, and product-trend pages above
Decision: absorbed / absorb_now; raw hash sha256:589d0e3ee14ec752caf94bd7a6f58865482768bf04dbce3cf3a4e9c7da80be87. Follow Builders was skipped because this was a Twitter-only morning slot. Ordinary announcements, repeated Skill/routing material, promotions, and unverified claims remained raw-only or Pending Jean review.
Pending Jean review: all seven touched pages remain ai_draft or equivalent; verify Projects rollout and quota behavior, lab metric definitions, Jev calibration, accepted-result/rework measurements, and route-level cost traces in primary sources or bounded local tests.
[2026-09-18] absorb | AI Briefing 2026-09-18 Afternoon
Pages touched: harness-engineering/agent-memory-as-hint-surface, harness-engineering/model-routing, harness-engineering/agent-trust-verification Key additions: promoted shared project memory to a multi-source concept; added calibrated decision models to routing; added parser-to-SSO-to-connected-account trust-chain evidence. Files processed:
- AI Briefing 2026-09-18 Afternoon → absorbed
- AI Builders Digest 2026-09-18 → raw only (duplicate source material already merged into the afternoon briefing)
Pending Jean review:
- harness-engineering/agent-memory-as-hint-surface — keep as ai_draft or revise the provenance and conflict-resolution questions.
- harness-engineering/model-routing — keep as ai_draft or test one reversible Jev-style routing decision.
- harness-engineering/agent-trust-verification — keep as ai_draft or verify against the primary incident report.
[2026-09-18] absorb | AI Briefing 2026-09-18 Evening 23-00
Pages touched: claude-code/overview, harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/self-verification-loops, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/skill-engineering-as-algorithm, harness-engineering/ai-security-speed-mismatch
Key additions: treated Projects as a project-level coordination layer with per-Thread evidence; separated Jev-style narrow routing from open-ended reasoning; connected Vibe Coding QA to runtime and security evidence; added reversibility and blast radius to PR review; kept connected-service privilege and account-incident claims behind explicit verification boundaries.
Files processed:
- AI Briefing 2026-09-18 Evening → existing Claude Code, routing, trust verification, self-verification, systems engineering, skill engineering, and security pages
Decision: absorbed / absorb_now; raw hash sha256:6729f20eb64b23283c7f6a2678a678734279119baf5576b42599940b9aaefa02.
Pending Jean review: all seven touched pages remain ai_draft; verify per-Thread evidence, Jev calibration and false negatives, runtime/security acceptance, PR review speed, skill invariants, and connected-service privileges in bounded local tests. The account-takeover item is an unverified social-media claim and remains a lead, not an established incident.
2026-09-18 newsletter absorb:Every 与 Ben's Bites
- Every:Why You Should Burn More Tokens
- Ben's Bites:New home for Cowork
- 选择性更新:harness-engineering/ai-cost-governance、harness-engineering/model-routing、harness-engineering/multi-agent-coordination-patterns、claude-code/overview、harness-engineering/agentic-software-is-systems-engineering。
- 主题增量:token 用量与反馈回路、阶段化模型与执行表面路由、并行 Agent 的收口、Cowork 统一入口、软件工厂的审查吞吐量。
- 两条原始来源均保留在 raw;未创建 newsletter 专属 Wiki 页面。供应商 benchmark、产品开放范围、融资估值和 Union Alpha 的安全传闻均保留证据边界,标记为 ai_draft / Pending Jean review。
Pending Jean review
- 在一个可回滚任务中验证 token、并行度、反馈暂停点、实际模型、执行表面、权限、测试、返工与 accepted result,再决定是否采纳来源中的阈值或产品判断。
[2026-09-19] absorb | 3 files (briefing 2026-09-17 evening, Ben's Bites 2026-09-16, Every 2026-09-16)
Pages touched: harness-engineering/model-routing, harness-engineering/fat-skills-fat-code-thin-harness, product-trends/software-factory-ladder, harness-engineering/single-master-agent-pattern, harness-engineering/compound-engineering, product-trends/forward-deployed-engineer, claude-code/self-improving-skills, product-trends/responsible-agenting, harness-engineering/folder-is-the-agent, ai-ecosystem/anthropic-ai-accelerated-offense, harness-engineering/ai-cost-governance, product-trends/ai-writing-tells, harness-engineering/computer-use-best-practices, product-trends/codex-team-methodology Key additions: probability-output judges as cheap routers; skill thinning as expiring bets; agent permission visibility; Arslan plan repo as externalized agent state; Sept 2026 Anthropic threat report; connector-vs-computer-use boundary; Codex review bottleneck. Files processed:
- AI Briefing 2026-09-17 Evening → harness-engineering/model-routing 等 7 页
- Ben's Bites 2026-09-16 → product-trends/responsible-agenting 等 6 页
- Every 2026-09-16 → harness-engineering/computer-use-best-practices、product-trends/codex-team-methodology
Pending Jean review
- harness-engineering/single-master-agent-pattern — 晋升为 mature(2 sources),ai_draft;建议:验证"单协调器+窄 MCP 够用"是否适用于 Jean 的工作台。
- product-trends/ai-writing-tells — 晋升为 mature(2 sources),ai_draft;建议:keep draft,Pangram 数据为单一实验。
- product-trends/responsible-agenting — ai_draft;建议:可为个人 agent 建权限表,验证后再升级。
2026-09-19 — DHH Lex Fridman #501 吸收
- Source:
raw/social-triage/2026-09-19 DHH Lex Fridman 501 编程已死编程万岁.md(YouTube,5h16m 逐字稿,Supadata 拉取) - Output:
outputs/2026-09-19-lex-fridman-501-dhh-agentic-engineering.md(中文整理文章,十章) - 合并进
harness-engineering/dhh-agentic-engineering(3→4 sources,按 Theme Aggregation Rule 4 合入既有 builder 页,未建独立页) - 新增洞察:agentic 四阶段划分、TTE 模型成本实证表、过度规格化伤害 agent(系统提示词 -80%)、交叉模型审查工作流
- 状态:全部 ai_draft,Pending Jean review
[2026-09-19] absorb | AI Briefing 2026-09-19 Morning 08-05
Pages touched: claude-code/agents-md-as-contract, claude-code/overview, ai-ecosystem/model-labs-becoming-agent-labs, ai-ecosystem/meta-muse-spark, harness-engineering/portable-agents-adward28, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, harness-engineering/model-routing, harness-engineering/ai-security-speed-mismatch, harness-engineering/ai-cost-governance, product-trends/cli-as-agent-interface, product-trends/agent-native-architecture
Key additions: AGENTS.md 兼容层与 Claude Projects 的项目运行面、独立评估能力、Muse 外部动作与 Connector、Agent 配置可移植性、Jev 决策路由与安全边界、Generative UI,以及 accepted output 驱动的成本治理。Hermes 产品方向、重复的 Skill/AGENTS 反应、促销和未经核实的安全或军事事件保留 raw-only 或 Pending Jean review。
Files processed:
- AI Briefing 2026-09-19 Morning → existing Claude Code, AI ecosystem, harness, and product-trend pages above
Decision: absorbed / absorb_now; raw hash sha256:ac0eeb6551056a8dca595240e6b5a8455e1ffb382869f00533bb3f3561fcd1d0. Follow Builders was skipped because this was a Twitter-only morning slot. No standalone briefing page was created.
Pending Jean review: all twelve touched pages remain ai_draft or equivalent; verify AGENTS.md precedence, Project Thread isolation, evaluation independence, Muse consent and revocation, portability manifests, Jev calibration, security harness isolation, and Generative UI acceptance evidence.
[2026-09-19] ingest | Eero Alvar《How I Use AI to Learn Things》
Pages touched: 无(新 builder,页面待 Jean 批准后创建) Key additions: AI 一对一学习三阶段系统(探测/规划/教学),与 Taste Skill / learning-mentor 同构。
[2026-09-19] ingest | Dwarkesh × Noam Brown — Agent 集群与 RSI
Pages touched: ai-ecosystem/dwarkesh-patel-ai-podcast, harness-engineering/multi-agent-coordination-patterns Key additions: 多智能体信用归属警示、极简协作脚手架、独立解题局部最优、评估视野问题。
[2026-09-19] page-created | AI 一对一学习系统(Eero Alvar)
Pages touched: mental-models/ai-one-on-one-learning Key additions: 应 Jean 批准,为 Eero Alvar 学习系统源卡片创建概念页(ai_draft,candidate,单来源)。
[2026-09-19] absorb | AI Briefing 2026-09-19 Afternoon 17-42
Pages touched: ai-ecosystem/llm-inference-mechanics, harness-engineering/model-routing, harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering
Key additions: diffusion-language-model inference as a full-stack serving question; high confidence cannot detect omitted business rules; exact-object evidence, fail-closed gates, receipts, and external-state reconciliation; independent health checks for the monitoring chain.
Files processed:
- AI Briefing 2026-09-19 Afternoon → selectively absorbed into four existing pages
- AI Builders Digest 2026-09-19 → raw only (
skipped_duplicate; fresh digest already merged into the afternoon briefing)
Decision: absorbed / absorb_now; raw hash sha256:8863ec6a60b3d70c9ef82b66170b39a945462086dc454f18f0ef8bdfe603f4c8. Repeated AGENTS.md, MCP Skills, product announcements, and lower-confidence claims remained raw-only or Pending Jean review.
Pending Jean review: all four touched pages remain ai_draft; independently benchmark Mercury-style diffusion inference, run an omission audit beside one classifier, test exact-chain receipts on a low-risk automation, and add one minimal monitor-health check.
[2026-09-19] absorb | AI Briefing 2026-09-19 Evening 22-58
Pages touched: forecasts/post-labor-economics, harness-engineering/agent-driven-qa
Key additions: separated a secondary-source account of conditional AI macro scenarios from wage/employment forecasts; added a user-centered acceptance surface for generated-code behavior, runtime performance, and basic security, with explicit review limits.
Files processed:
- AI Briefing 2026-09-19 Evening → selectively absorbed into two existing pages
Decision: absorbed / absorb_now; raw hash sha256:61ab71791030d22e71f75884037afaffa232ea7cbf78581bd3bc9046f87de02d. Overlapping Muse, Jev, and coding-workflow material was already represented in existing pages or same-day briefings; lower-confidence product claims remain raw-only. No standalone briefing page created.
Pending Jean review: both touched pages remain ai_draft; verify the scenario details against Anthropic's original paper, and trial the three-part acceptance checklist on a low-risk project while keeping separate evidence for each dimension.
2026-09-19 absorb | Every: Vibe Check: Is Astra a Breakthrough for Indie Filmmakers?
- File: Every 2026-09-19 VFX case
- Updated: product-trends/code-native-visual-ai
- Key addition: promoted the existing single-source candidate by synthesizing the code-render-inspect framework with a hybrid VFX case using Python, Blender, specialist matting, Nuke, and human-directed local revisions; retained limits around organic forms, physical interaction, and the absence of cost or independent benchmark data.
- Decision: absorbed into the existing concept. No standalone newsletter page created. Absorb state and source hash recorded in wiki/_absorb_log.json.
Pending Jean review
- product-trends/code-native-visual-ai — ai_draft; compare one bounded pixel-native visual task with an editable code/render loop, including artifact quality, editability, human time, and rework.
[2026-09-19] absorb | tool-backlog 登记(raw_only)
Files processed:
- 待尝试工具清单 → raw_only(Jean 私人待试工具清单,living file;按文件头规则,试用产生洞见后才入 wiki,本次不建页)
[2026-09-20] absorb | 2026-09-19 social-triage 三源补登记(absorb_now)
三份 2026-09-19 源卡片的内容已在前一日写入 wiki,本次扫描发现 _absorb_log.json 缺少对应条目,按内容覆盖核对后补登记(hash 为本次观测值)。
Files processed:
- Lex #501 DHH → harness-engineering/dhh-agentic-engineering(2026-09-19 区块:四阶段划分、过度规格化、TTE 成本实证、交叉模型审查)
- Eero Alvar AI 学习系统 → mental-models/ai-one-on-one-learning(candidate,三阶段探测/规划/教学)
- Noam Brown × Dwarkesh → ai-ecosystem/dwarkesh-patel-ai-podcast、harness-engineering/agent-trust-verification、harness-engineering/multi-agent-coordination-patterns
Decision: absorbed / absorb_now × 3;raw hashes 已写入 wiki/_absorb_log.json(41f4c3fc…、1ffd7aeb…、acb391d5…)。
Pending Jean review
- mental-models/ai-one-on-one-learning — candidate /
ai_draft(单源);建议:等待第二来源或 Jean 亲测 learning-mentor 吸收探测环节后再定去留。 - harness-engineering/dhh-agentic-engineering 2026-09-19 区块 —
ai_draft;视频时间戳基于转写 offset,成本数字为 DHH 口述未独立验证。 - harness-engineering/agent-trust-verification 前沿对齐三问题区块 —
ai_draft;Noam 关于 CoT 可监控性退化的说法为其单方面口径,无公开数据。
[2026-09-20] absorb | AI Briefing 2026-09-20 Morning 08-16
- File: AI Briefing 2026-09-20 Morning
- Updated: harness-engineering/judgment-engineering, harness-engineering/agent-session-history-as-asset, harness-engineering/matt-pocock-ai-coding-workflow, product-trends/human-agent-interaction
- Key additions: Jev Claude Code 路由与决策模型评测边界;Agent session 生命周期及 cloud/local 执行状态;领域术语作为 prompt 假设;全局监督所需的人类节奏。
- Decision:
absorbed/absorb_now; source hashsha256:c838c185c00dd36402882a8743c8e8ef08dce141d2740c5e5fd0cb937c4432f2。无 Follow Builders 合并,未创建独立简报页。 - Files processed:
- AI Briefing 2026-09-20 Morning → 上述四个既有页面
- Raw-only: 低置信度 Mistral 转向说法、单次固件/交易案例及普通产品公告;Dotey QA 重复项已在 9/19 吸收,本次不重复。
Pending Jean review
- harness-engineering/judgment-engineering —
ai_draft;校准固定决策任务并比较规则/模型选项。 - harness-engineering/agent-session-history-as-asset —
ai_draft;验证 trace 与摘要状态的取舍及 cloud/local handoff。 - harness-engineering/matt-pocock-ai-coding-workflow —
ai_draft;比较领域词汇与普通语言 prompt 的效果。 - product-trends/human-agent-interaction —
ai_draft;对照 paper-first 与 bounded agent plan 的打断、返工和控制成本。
[2026-09-20] ingest | AI Skills with Matt Pocock (Pragmatic Engineer)
Pages touched: matt-pocock-ai-coding-workflow, skills-into-loops Key additions: Pragmatic Engineer 访谈一手来源——leading words 机制确认、smart zone 量化(150k)、memento-driven development、wayfinder DAG、shift-right 对齐框架、TDD 修正观点、gardening/platform team;源卡片 raw/social-triage/2026-09-20 Matt Pocock AI Skills Pragmatic Engineer.md;文章 outputs/2026-09-20-matt-pocock-ai-skills.md。
[2026-09-20] absorb | AI Briefing 2026-09-20 Afternoon 17-41
Pages touched: harness-engineering/agentic-software-is-systems-engineering, harness-engineering/agent-trust-verification, harness-engineering/model-routing, product-trends/agent-native-architecture
Key additions: generation throughput must stay below review and understanding capacity; LLM judges require human-label calibration; cache-rate claims need route-level evidence; personal and work agents may require separate principals, credentials, and audit boundaries.
Files processed:
- AI Briefing 2026-09-20 Afternoon → selectively absorbed into four existing pages
- AI Builders Digest 2026-09-20 → raw only (
skipped_duplicate; fresh digest already merged into the afternoon briefing)
Decision: absorbed / absorb_now; raw hash sha256:49a263bcf7a688c49c0c5dd0ab550aedce5c2d43cbecd3289ef29a9b8e8c4370. Product announcements, community tool lists, and unverified security or biology claims remained raw-only or Pending Jean review.
Pending Jean review: all four touched pages remain ai_draft; measure review-bound throughput, calibrate one judge against human labels, trace one provider route and cache claim, and map one personal/work workflow by principal and credential owner.
2026-09-20 21:25 | EMERGE | raw emergent themes | outputs/ideas/2026-09-20-raw-emergent-themes.md
[2026-09-20] absorb | AI Briefing — 2026-09-20 (evening)
Pages touched: harness-engineering/computer-use-best-practices Key additions: recorded a developer-reported computer-use workflow for repetitive app lifecycle QA, with caveats about test coverage and destructive actions. Pending Jean review: verify the test scope, sampling, false positives, and permission boundaries before reusing the approach.
[2026-09-20] absorb | Every — Copy Our Homework
Pages touched: writing/writing-with-ai Key additions: added Mike Taylor's source-material-first and author-accountability framework to the existing AI-writing concept. The computer-use, folder, token-cost, and VFX recaps matched already absorbed Every issues; no standalone newsletter page was created. Files processed:
- Every — Copy Our Homework → writing/writing-with-ai
Decision:
absorbed/absorb_now; raw hashsha256:140a8b5cca126d200bbeb778f8d4da7136b8a6bdea88f72dcf598bf6150515df.
Pending Jean review
- writing/writing-with-ai —
ai_draft; test the author-material rule against one real draft and confirm claim provenance and voice.
[2026-09-21] absorb | AI Briefing 2026-09-21 Morning 08-16
Pages touched: product-trends/stripe-agent-native-economy, harness-engineering/agent-session-history-as-asset
Key additions: promoted the Stripe Agent Economy candidate by synthesizing the interview summary with a user-reported delegated-purchase example and an attributed B2A forecast; added a separate request for local Codex/Claude history to the existing session-history concept.
Files processed:
- AI Briefing 2026-09-21 Morning → the two existing pages above
Decision: absorbed / absorb_now; source hash sha256:2241636a565bb196dc74b79541cf9498fb606856e3985ecf8a94376183c9feae. Repeated Jev, Matt, Claude Projects, and Mole items already represented in 9/20 briefings were not added again; low-confidence secondary reporting, product announcements, and unverified demos/cost claims remain raw-only. No standalone briefing page created.
Pending Jean review
- product-trends/stripe-agent-native-economy —
ai_draft; validate one delegated purchase path: principal, permissions, limits, confirmation, receipt, and reversal. - harness-engineering/agent-session-history-as-asset —
ai_draft; verify whether local history should index full transcripts or selected task states and how access/retention/deletion are exposed.
[2026-09-21] absorb | Every — How to Create Your Own Personal AI Benchmark
Pages touched: harness-engineering/personal-ai-benchmark, harness-engineering/model-routing, wiki/index Key additions: 新建候选概念页 personal-ai-benchmark(三层构建方法、辨识地平线、pass/fail rubric、基准过期);model-routing 增加 owned evals 操作层段落。 Files processed:
[2026-09-22] ingest | Why We Made Jev (Latent Space) + jev-engineering-zh 两份文档
Pages touched: ai-ecosystem/jev Key additions: 播客一手声音纠正「decision model」命名为 system one model;RLCD/RLVR 谱系与「零 RLVR」赌注;coding agent 战局与 KV cache 解放邀约;API 实践指南;汇编版对原始笔记的柔化标注。 Output: outputs/2026-09-22-jev-kv-cache-rules-everything.md
[2026-09-23] absorb | AI Briefing 2026-09-23 Afternoon
Pages touched: ai-ecosystem/claude-opus-55-evaluation (new), harness-engineering/advisor-pattern, forecasts/jevons-paradox-ai-scope-expansion, ai-ecosystem/jev, harness-engineering/agent-trust-verification
Key additions: Opus 5.5 发布即默认化与多源实测汇总(105-bug、HAProxy 移植、Box 企业数据、Next.js evals);dotey 的 Fable advisor 验收闭环;前沿定价双降下的每任务成本数据(Jevons 应用);Jev 的 OpenRouter 使用数据与 vibecoder relations 生态信号;e2e 举证、Lean/TLA+ 形式化验证与每线程 worktree 隔离的验证趋势。 Files processed:
- AI Briefing 2026-09-23 Afternoon → 四个更新页 + 新页
- AI Builders Digest 2026-09-23 → skipped_duplicate(内容已verbatim并入简报)
Decision: absorbed / absorb_now; source hash sha256:18b72eeaf1b7cc8611be678422400572ee0fbb485fb7e5aae48ef4e5ba1b4260. No standalone briefing page created.
Pending Jean review
- ai-ecosystem/claude-opus-55-evaluation —
ai_draft; 自测一轮 105-bug 式冒烟测试验证「与 Fable 5.1 持平、成本更低」。
[2026-09-22] absorb | Ben's Bites — What can you build with Jev
Pages touched: ai-ecosystem/jev, product-trends/agent-native-architecture
Key additions: Jev 开放后一周约 100 个社区集成,补充了其作为工具内部分类、路由和完成度判断层的生态证据;Amazon 封锁 Meta Muse 的案例补充了 agentic commerce 中平台参与、客户关系起点和交易控制的结构性张力。
Files processed:
- Ben's Bites — What can you build with Jev → ai-ecosystem/jev, product-trends/agent-native-architecture
Decision: absorbed / absorb_now; raw hash sha256:f06995036a2bad772d9d3bfec219fc37b034ecf7e997e51f9ddbdf0cf105e7a6.
Pending Jean review
- ai-ecosystem/jev —
ai_draft; verify the community-project count, quality, and local calibration before treating the ecosystem as evidence of reliable adoption. - product-trends/agent-native-architecture —
ai_draft; decide whether platform participation and customer-relationship ownership should become a core product test for agentic commerce.
[2026-09-23] ingest | AI Briefing 2026-09-23 Evening
Pages touched: ai-ecosystem/claude-opus-55-evaluation, ai-ecosystem/jev, ai-ecosystem/qwen-36-agent-leap, claude-code/agents-md-as-contract, harness-engineering/advisor-pattern, harness-engineering/agent-trust-verification, harness-engineering/computer-use-best-practices, harness-engineering/ai-cost-governance
Key additions: Twitter-only evening briefing added current signals on model effort and cost, structured mobile agents, system-one framing, documentation contracts, advisor loops, formal verification, accessibility-based computer use, and agent cost governance.
Files processed:
- AI Briefing 2026-09-23 Evening → selected existing wiki pages
Pending Jean review
- The touched pages remain ai_draft; verify the model comparisons, benchmark scope, and workflow claims before promoting any interpretation.
[2026-09-24] absorb | 30-day scan + Every personal benchmark + Jev 源卡片补遗
Pages touched: harness-engineering/personal-ai-benchmark, ai-ecosystem/jev Key additions: 30 天扫描 141 个 raw 文件,138 个已在 log;Every 个人基准通讯确认已有候选页覆盖(补记 log);jev 页补充播客「谨慎点」(vision 未接入、API 安全对齐定位)。 Files processed:
- Every — Personal AI Benchmark → harness-engineering/personal-ai-benchmark(已存在候选页,补记)
- Diogo Almeida — Why We Made Jev → ai-ecosystem/jev(补 Counterpoints:vision/安全对齐/自动交易边界)
[2026-09-24] absorb | AI Briefing 2026-09-24 Morning 08-05
Pages touched: harness-engineering/agent-session-history-as-asset, harness-engineering/folder-is-the-agent, harness-engineering/model-harness-fit
Key additions: added official cloud-session and local-Projects evidence to session history; added progressive-disclosure documentation as the navigation layer for folder-based agents; and added an attributed model-market-fit observation to the existing model-harness concept.
Files processed:
- AI Briefing 2026-09-24 Morning → the three existing pages above
Decision: absorbed / absorb_now; source hash sha256:c7636cf759c668ed851ae7d553051a5c10701078318a8140cf155ea2930d7da8. Repeated 2026-09-23 items were not added again; product announcements, personal model preferences, unverified Google AX claims, and one-off demos remain raw-only. No standalone briefing page created.
Pending Jean review
- harness-engineering/agent-session-history-as-asset —
ai_draft; verify whether cloud continuation and local execution should share one history model or expose separate retention, permissions, and handoff states. - harness-engineering/folder-is-the-agent —
ai_draft; compare indexed progressive-disclosure docs with a monolithic instruction file by retrieval errors, stale-rule rate, and task recovery time. - harness-engineering/model-harness-fit —
ai_draft; compare two harnesses on the same multi-step task using time-to-accepted-result, per-step latency, total cost, retries, and willingness to reuse.
[2026-09-24] absorb | AI Briefing 2026-09-24 Afternoon 17-41
Pages touched: harness-engineering/managed-agents-architecture, ai-ecosystem/agent-infrastructure-trends, claude-code/overview
Key additions: merged Anthropic containment and Managed Agents evidence into existing architecture pages, including approval fatigue, pre-trust configuration parsing, capability-scoped egress, durable session recovery, and public-build regression controls. The Builders digest was logged as raw-only because it was already merged into the briefing.
Files processed:
- AI Briefing 2026-09-24 Afternoon → three existing wiki pages
- AI Builders Digest 2026-09-24 → skipped duplicate; merged into the briefing
Decision: briefing absorbed / absorb_now; source hash sha256:87c65b477972d836b84db767926ecbc1f613aedd68fede37a9ac160ff9b4ef41. Digest skipped_duplicate / raw_only; source hash sha256:029dd908310ee6cff0e76993256b37e4a20b151beea59eda4a9563bd530e945e.
Pending Jean review
- harness-engineering/managed-agents-architecture —
ai_draft; verify session recovery, sandbox replacement, tool retry, and event replay on a bounded task. - ai-ecosystem/agent-infrastructure-trends —
ai_draft; map one local Agent toolchain's credential, file, network, tool, and event-log boundaries. - claude-code/overview —
ai_draft; test trust-prompt ordering, sandbox network defaults, and one stale-session regression case.
[2026-09-24] absorb | AI Briefing 2026-09-24 Evening 22-58
Pages touched: harness-engineering/agent-storage-compute-separation, harness-engineering/agentic-infrastructure, harness-engineering/self-verification-loops, claude-code/agents-md-as-contract, ai-ecosystem/claude-opus-55-evaluation, ai-tools/ai-writing-guardrails, claude-code/personal-agent-minimal-setup, harness-engineering/agent-trust-verification
Key additions: merged timeline evidence on agent storage/compute separation, harness self-verification, AGENTS.md contracts, Opus evaluation framing, writing guardrails, minimal personal-agent setup, and trust verification. Twitter-only claims remain marked as ai_draft pending Jean review; no Follow Builders material was merged.
Files processed:
- AI Briefing 2026-09-24 Evening → the eight existing wiki pages
Decision: briefing absorbed / absorb_now; source hash sha256:3ae2094670f54231e649c61470a0c2382b921faf1ddd4be8aefed1030c7f7466.
Pending Jean review
- Existing pages above remain
ai_draft; verify the linked claims against primary sources before promotion tohuman_verified.
[2026-09-24] absorb | Every — How to Get the Most Out of Jev / Ben's Bites — Back to Claude
Pages touched: ai-ecosystem/jev, ai-ecosystem/claude-opus-55-evaluation
Key additions: Jev 模糊问题拆解工作流(工作定义 → 离散加权检查 → 小样本校准 → 全量)与「10 秒规则」;意图驱动软件交互范式;Together Tev1-4B 开源判断模型($17 自训)作为判断层商品化首个公开佐证;Opus 5.5 的 Codex 回流信号与限额经济学(Sol 4h 长任务消耗 $100 档 22% 周限额)。
Files processed:
- Every — How to Get the Most Out of Jev → ai-ecosystem/jev
- Ben's Bites — Back to Claude → ai-ecosystem/jev, ai-ecosystem/claude-opus-55-evaluation
Decision: absorbed / absorb_now; raw hashes sha256:62266c721c147d3387b7cb2c7cd974d60a0c2a61105e7861d5e6fc949dc6ad79 (Every) and sha256:61f21a219491a7ead7f04ecdada5cbb16f783ecece0e2396d166bc8690c87f9a (Ben's Bites). No standalone newsletter page created.
Pending Jean review
- ai-ecosystem/jev —
ai_draft; 用本地标注样本验证「模糊问题拆解」工作流后再将其作为 harness 判断层的操作指引。 - ai-ecosystem/claude-opus-55-evaluation —
ai_draft; 记录一次自己的长任务限额消耗,与 22%/4h 基线对照后再更新默认模型判断。
[2026-09-25] absorb | AI Builders Digest 2026-09-23 (re-scan)
Pages touched: none Key additions: no new content; digest confirmed duplicate of raw/briefing/AI Briefing/2026-09-23-17-58.md, repair absorb log entry with raw-file hash. Files processed:
- raw/briefing/AI Builders Digest/2026-09-23.md → skipped_duplicate (content merged into AI Briefing 2026-09-23-17-58)
[2026-09-25] absorb | AI Briefing 2026-09-25 Morning
Pages touched: harness-engineering/agent-driven-qa, harness-engineering/agent-trust-verification, harness-engineering/multi-agent-coordination-patterns, harness-engineering/personal-ai-benchmark, product-trends/agent-native-architecture, product-trends/stripe-agent-native-economy
Key additions: OpenClaw test-suite audit as a quality signal; inspectable agent state and user-scoped connectors; permissioned Agent-to-Agent context exchange; work-embedded model benchmarks; connector distribution and delegated subscription actions.
Files processed:
- AI Briefing 2026-09-25 Morning → six concept pages above
Decision: absorbed / absorb_now; raw hash sha256:1edd5cb1d9538326ef19dbd1e922de600b10d1c025e33805c15f9e69bf4ddc64. Twitter-only morning slot; repeated themes, product announcements, demos, and subjective model claims remain raw-only. No standalone briefing page created.
Pending Jean review
- harness-engineering/agent-driven-qa —
ai_draft; audit one bounded local test family using behavior coverage, failure history, maintenance cost, and post-change regression evidence. - harness-engineering/agent-trust-verification —
ai_draft; expose readback evidence for memory writes, scheduled jobs, tool calls, token spend, and connector scope. - harness-engineering/multi-agent-coordination-patterns —
ai_draft; test a low-risk Agent-to-Agent request with explicit principal, source, field scope, approval, and audit log. - harness-engineering/personal-ai-benchmark —
ai_draft; build a ten-task benchmark with rubric, harness version, and accepted results. - product-trends/agent-native-architecture —
ai_draft; map one connector workflow from intent through permission, result, receipt, and fallback. - product-trends/stripe-agent-native-economy —
ai_draft; validate principal, scope, approval, receipt, and reversal in one low-risk subscription flow.
[2026-09-25] absorb | AI Briefing 2026-09-25 Afternoon 17-41
Pages touched: harness-engineering/advisor-pattern, harness-engineering/model-routing, ai-ecosystem/agent-infrastructure-trends, claude-code/overview
Key additions: added the three-node advisor loop, routing observability, permissioned Agent-to-agent context exchange, and Claude Code custom mode/configuration evidence to existing pages. Announcements, personal model claims, and one-off demos remain raw-only. The Builders digest was logged as duplicate because it was merged into the briefing.
Files processed:
- AI Briefing 2026-09-25 Afternoon → four existing wiki pages
- AI Builders Digest 2026-09-25 → skipped duplicate; merged into the briefing
Decision: briefing absorbed / absorb_now; raw hash sha256:0aa2f454a489439750808bbaa55567c7cbae67997d5eba9a784862ab8cf3539a. Digest skipped_duplicate / raw_only; raw hash sha256:35122f81d2c54111dc76cfaf45d6eafc73cb67bcfd9245d2f8fc3a699e8aeb4b.
Pending Jean review
- harness-engineering/advisor-pattern —
ai_draft; compare three-node advisor loop with single-model execution on cost, rework, acceptance rate, and information exposure. - harness-engineering/model-routing —
ai_draft; record effective model, route reason, fallback, latency, cost, and accepted result on one multi-model task. - ai-ecosystem/agent-infrastructure-trends —
ai_draft; prototype a read-only Agent-to-agent context request with identity, authorization, provenance, revocation, and audit events. - claude-code/overview —
ai_draft; test a read-only custom mode against CLAUDE.md/AGENTS.md priority, visibility, and rollback.
[2026-09-25] absorb | AI Briefing 2026-09-25 Evening 22-58
Pages touched: harness-engineering/agent-storage-compute-separation, harness-engineering/agentic-infrastructure, claude-code/auto-mode, ai-ecosystem/claude-opus-55-evaluation, harness-engineering/factory-missions-architecture
Key additions: merged timeline evidence on agent runtime separation, scheduler controls, Auto Mode rollout, Opus 5.5 long-task and cost signals, and independent test auditing. No Follow Builders material was merged.
Files processed:
- AI Briefing 2026-09-25 Evening → the five existing wiki pages
Decision: briefing absorbed / absorb_now; source hash sha256:4bd5fc21a24b3f63848f673c0c912c85f5eb84c096d61223d188e2a8cc7d9bf9.
Pending Jean review
- harness-engineering/agent-storage-compute-separation, harness-engineering/agentic-infrastructure, claude-code/auto-mode, ai-ecosystem/claude-opus-55-evaluation, harness-engineering/factory-missions-architecture — ai_draft; verify the new claims against primary sources and bounded local tests.
[2026-09-25] absorb | Every — Why Evals Are So Hot Right Now / Ben's Bites — 50 years of tech devices
Pages touched: harness-engineering/personal-ai-benchmark, product-trends/agent-native-architecture
Key additions: evals 主流化证据(PM 岗位近半要求 evals 经验、Sentry 每月约 1,800 次 eval 运行)推动 personal-ai-benchmark 从 candidate 升为 mature;「Slack agents 是新的网站」门面论与 here.now 一句话发布/挂载能力合入 agent-native-architecture 的零门槛分发供给面观察。Grok 4.7 场景级分裂证据(基准 42% vs 重度用户 daily driver)作为基准必要性的反面教材记录,未建独立页。
Files processed:
- Every — Why Evals Are So Hot Right Now → harness-engineering/personal-ai-benchmark, product-trends/agent-native-architecture
- Ben's Bites — 50 years of tech devices → product-trends/agent-native-architecture
Decision: absorbed / absorb_now; raw hashes sha256:a93436daeaef37c73aaf5d06ae851b27157d869e091253f3788b51f662469043 (Every) and sha256:2d9844671a3eacfc5409dba1638e561a296690fd0bf8bc617ded704c99d2d269 (Ben's Bites). No standalone newsletter pages created.
Pending Jean review
- harness-engineering/personal-ai-benchmark —
ai_draft; 用下次模型发布触发一次「基准先行」实践,验证发布筛选 workflow。 - product-trends/agent-native-architecture —
ai_draft; 评估是否把对话平台入口纳入自己的 intake 面设计。
[2026-09-26] absorb | Matt Pocock (Pragmatic Engineer) 第二来源晋升批次
Pages touched: claude-code/memento-driven-development, harness-engineering/smart-zone-context-efficiency, harness-engineering/grill-me-values-consensus, harness-engineering/tdd-evidence, mental-models/wayfinder-project-map, writing/leading-words-longform-motifs Key additions: 6 个单源 candidate 页以 Matt Pocock × Pragmatic Engineer 访谈为第二来源晋升为 mature,各自补入机制层新证据(memento 的环境论、聪明区与窗口无关、grill me 35 问与价值层级显式化、tautological tests、wayfinder ticket 类型 DAG 与跨域复用、leading words 书单与咒语机制)。 Files processed:
- Matt Pocock on The Pragmatic Engineer → 6 页 candidate→mature 晋升
- Every — Personal AI Benchmark → 覆盖已完整(personal-ai-benchmark, 3 sources),仅更新 hash
- Diogo Almeida — Why We Made Jev → 覆盖已完整(ai-ecosystem/jev, system one 命名修正已落地),仅更新 hash
Pending Jean review
- 六页均保持
knowledge_status: ai_draft;第二来源为同一作者(Matt Pocock)在另一场合的重述,属"同证人二次陈述"而非独立证人,判断置信度提升有限,建议保持 draft 观察是否有第三方独立来源。
[2026-09-26] absorb | AI Briefing 2026-09-26 Morning
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/zero-trust-ai-agents, harness-engineering/self-verification-loops, harness-engineering/personal-ai-benchmark, harness-engineering/judgment-engineering, product-trends/agent-native-architecture
Key additions: locked-down agents and independent verification; external-service data boundaries; staged reasoning effort and enterprise eval loops; work-embedded benchmarks; interpretable judgment and routing traces; personal and enterprise agent-native workspaces.
Files processed:
- AI Briefing 2026-09-26 Morning → six concept pages above
Decision: absorbed / absorb_now; raw hash sha256:e1609e30e237a7cf28304b539d554b2de7d50946f2c148c8af86d883f5970aee. Twitter-only morning slot; product updates, demos, subjective model claims, outage posts, and repeated items remain raw-only. No standalone briefing page created.
Pending Jean review
- harness-engineering/agent-trust-verification —
ai_draft; configure an action allowlist, independent verifier, and machine-readable improvement evidence for one high-risk local task. - harness-engineering/zero-trust-ai-agents —
ai_draft; define deny-by-default external uploads, data classes, endpoint allowlists, and deletion readback for one eval environment. - harness-engineering/self-verification-loops —
ai_draft; compare low-effort implementation plus high-effort verification with an all-high-effort baseline. - harness-engineering/personal-ai-benchmark —
ai_draft; define ten real data-query tasks with field permissions, rubric, and accepted outcomes. - harness-engineering/judgment-engineering —
ai_draft; preserve labels, effort, route choice, cost, and accepted result for one fixed task. - product-trends/agent-native-architecture —
ai_draft; map state, data boundaries, permissions, and fallback paths for one personal and one enterprise workspace.
[2026-09-26] absorb | AI Briefing 2026-09-26 Afternoon 17-39
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, claude-code/overview, ai-ecosystem/claude-opus-55-evaluation Key additions: Software Factory 的锁定环境、导航和验证基础设施;额度边界与可恢复收尾;effort、CODING_STANDARDS 和工作区导航共同塑造 runtime;以接受结果而非单次请求评估 Opus 5.5 的会话成本。 Files processed:
- AI Briefing 2026-09-26 Afternoon → four existing concept/overview pages
- AI Builders Digest 2026-09-26 → merged into briefing; raw-only duplicate
Decision: briefing absorbed / absorb_now; raw hash sha256:cf92fd4e2e42cafbf3661ba01905815b9e752b467a1a1fef2e28002a2fe6a1c0. Digest skipped_duplicate / raw_only; raw hash sha256:cd171e2512fed058870f67ad83c69d87313a09eca91f69ba31f9727c636830ac.
Pending Jean review
- harness-engineering/agent-trust-verification —
ai_draft; test quota-aware checkpoints and recoverable handoff on one cross-file task. - harness-engineering/agentic-software-is-systems-engineering —
ai_draft; compare feature-map navigation and independent verification against a normal repository workflow. - claude-code/overview —
ai_draft; measure effort, rule hits, navigation time, rework, and accepted results on a fixed task set. - ai-ecosystem/claude-opus-55-evaluation —
ai_draft; build a repeatable table of model, effort, context, turns, cost, rework, and acceptance.
[2026-09-26] absorb | AI Briefing 2026-09-26 Evening 22-57
Pages touched: harness-engineering/factory-missions-architecture, claude-code/auto-mode, ai-ecosystem/claude-opus-55-evaluation, harness-engineering/agentic-infrastructure, claude-code/plan-first-coding-agent
Key additions: merged timeline evidence on test auditing, coding standards, effort and prompt audits, Opus 5.5 long-task economics, personal operating systems, stateful connectors, and composable plan modes. No Follow Builders material was merged.
Files processed:
- AI Briefing 2026-09-26 Evening → the five existing wiki pages
Decision: briefing absorbed / absorb_now; source hash sha256:101b838af325872742e38fceed025eac8049ebdae63253c43bb37c43fa4a342d.
Pending Jean review
- harness-engineering/factory-missions-architecture, claude-code/auto-mode, ai-ecosystem/claude-opus-55-evaluation, harness-engineering/agentic-infrastructure, claude-code/plan-first-coding-agent — ai_draft; verify the new claims against primary sources and bounded local tests.
[2026-09-26] ingest | Every — Copilot Gets a Seat in the Org Chart
Pages touched: harness-engineering/personal-ai-benchmark, product-trends/agent-native-architecture, harness-engineering/multi-agent-coordination-patterns Key additions: 微软统一 Copilot 发布会报道;公司级 evals 成为组织实践(16k 内部 evals、人类基线先行);三大实验室统一入口之争与组织内 Agent 身份/治理;跨实验室强模型带弱模型两级委派模式。
Files processed:
- Copilot Gets a Seat in the Org Chart → harness-engineering/personal-ai-benchmark, product-trends/agent-native-architecture, harness-engineering/multi-agent-coordination-patterns
[2026-09-27] absorb | AI Briefing 2026-09-27 Morning
Pages touched: harness-engineering/agent-memory-vs-context-substrate, harness-engineering/self-verification-loops, harness-engineering/personal-ai-benchmark, product-trends/stripe-agent-native-economy, harness-engineering/agentic-software-is-systems-engineering, ai-ecosystem/jev
Key additions: relational memory and cold-start context; fresh-context minimization and independent verification; workflow-specific benchmark failure labels; provider and customer-ownership boundaries in agentic commerce; readable, deletable, and deny-by-default system controls; Jev as a narrow classification and routing layer. No Follow Builders material was merged.
Files processed:
- AI Briefing 2026-09-27 Morning → six existing wiki pages
Decision: briefing absorbed / absorb_now; source hash sha256:a878d65272d6088c736ad78b3c0fe5bf0a8250edad64a896baf2c8404a62273e.
Pending Jean review
- harness-engineering/agent-memory-vs-context-substrate, harness-engineering/self-verification-loops, harness-engineering/personal-ai-benchmark, product-trends/stripe-agent-native-economy, harness-engineering/agentic-software-is-systems-engineering, ai-ecosystem/jev — ai_draft; verify the new claims against primary sources and bounded local tests.
[2026-09-27] absorb | AI Briefing 2026-09-27 Afternoon 17-39
Pages touched: harness-engineering/agent-trust-verification, harness-engineering/agentic-software-is-systems-engineering, claude-code/overview, ai-ecosystem/claude-opus-55-evaluation Key additions: 环境预检与沙箱边界;观察、执行、结果、反馈的 Agent 行动回路;dashboard、Computer Use 与连接器组成的可观察工作台;保留任务分布的模型比较。 Files processed:
- AI Briefing 2026-09-27 Afternoon → four existing concept/overview pages
- AI Builders Digest 2026-09-27 → merged into briefing; raw-only duplicate
Decision: briefing absorbed / absorb_now; raw hash sha256:0861a95c8b6132956ec73817efa3d5ebae138457325a97d5db304dbe44c3c90c. Digest skipped_duplicate / raw_only; raw hash sha256:db47307c925dcd3944d49f713de074744cbf8145ea6a5decb3aea01e2a5b4445.
Pending Jean review
- harness-engineering/agent-trust-verification —
ai_draft; test environment preflight, deny-by-default sandboxing, and over-scope action alerts. - harness-engineering/agentic-software-is-systems-engineering —
ai_draft; define action records, feedback fields, permissions, and deletion paths for one Agent workflow. - claude-code/overview —
ai_draft; record dashboard, Computer Use observation, handoff, permissions, and final acceptance evidence. - ai-ecosystem/claude-opus-55-evaluation —
ai_draft; compare Opus 5.5 and Astra on a fixed task distribution with cost and rework metrics.