@lilianweng: In the past few months, we had a lot of fun (and stress ) to produce 12 versions (+ many subversions) and 137 pages in …
Summary
Lilian Weng shares insights on the iterative process of creating a comprehensive training run logbook, highlighting the importance of human-human collaboration in improving human-AI collaboration.
View Cached Full Text
Cached at: 05/12/26, 04:46 AM
In the past few months, we had a lot of fun (and stress 😅) to produce 12 versions (+ many subversions) and 137 pages in our training run log book.
Turns out human-human collaboration is important to improving human-AI collaboration. 😊 https://t.co/kPucxYvXM4
Similar Articles
@huangtongxueh: Recently, I did an AI development sharing session for the team and casually turned it into an article. I wrote about ho…
An engineer at a major tech company shares their takeaways from two months of AI-assisted development, covering how to divide work across a combination of Codex, GPT-5.6 Sol, Astra, and Claude, and how a lean set of Skills paired with methodology prompts like first-principles thinking and adversarial review can replace heavyweight workflows in the era of stronger models and boost everyday dev efficiency.
@luoleiorg: Recently, I took some time to organize my AI workflow, turned it into a webpage, and wanted to share it with everyone h…
一位开发者公开了他的个人 AI 工作流网页，详细讲解如何用 Markdown 约定、UserPromptSubmit 钩子和外包脚本在 Claude、Codex、Kimi、Grok、Gemini 等多模型间做任务派单、成本分层与自动验收，形成一套被称为 harness 的第四代实践体系。
@lilianweng: new post on harness engineering for AI self-improvement: https://lilianweng.github.io/posts/2026-07-04-harness/… It is …
Lilian Weng's blog post explores the concept of harness engineering as a key component for recursive self-improvement in AI systems, discussing design patterns, workflow automation, and the analogy to operating systems.
@hocyzon: This is the blog of Lilian Weng, OpenAI's VP of Safety Research @lilianweng, and it's of very high quality. She once sh…
A post recommending Lilian Weng's blog Lil'Log, highlighting her seven-step research writing workflow and summarizing her posts on recursive self-improvement, scaling laws, test-time compute, and reward hacking.
@shao__meng: Seven Stages of AI-Driven Development 1. Grill 2. Research 3. Prototype 4. PRD 5. Issues 6. Implement 7. Review From Skills For Real Engineers by @…
A Twitter thread shares the seven stages of AI-driven development from the Skills For Real Engineers project by @mattpocockuk, including alignment techniques like grill sessions and tooling for coding agents.