Lilian Weng

In agentic AI systems, prompt engineering has evolved into context engineering: reliable behavior requires deliberate design of four components—system prompt, tools, examples, and context state management—otherwise, context rot causes behavioral drift across multi-step reasoning, as identified by Anthropic's research.

Lilian Weng总结35篇Harness Engineering论文，揭示其在AI自我改进中的核心作用，Meta与Anthropic的产品动态被重点提及。

AI自我改进工程（Harness Engineering）将推动自动研究，使模型在保持目标指定需求下持续进化。

扩展定律是深度学习中最重要的实证发现之一，它帮助我们预测模型规模和数据量对训练损失的影响。

The article explores extrinsic hallucinations in large language models, analyzing their causes, impacts, and detection methods.

Lilian Weng advocates for increased collaboration in human-AI interactivity and announces a $100,000 grant program by Thinking Machines, but the post lacks technical depth and serves primarily as a promotional announcement.

Human-to-human collaboration plays a key role in improving human-AI collaboration, as learned from maintaining a 137-page training log across 12 iterations.

该推文为个人职业感悟分享，缺乏具体技术内容和工程实践指导。

该推文为个人职业变动声明，未涉及具体技术内容或工程实践。