上下文工程：正确的300个token胜过10万个嘈杂token
原标题：Presentation: The Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering
AI 摘要
在InfoQ的演讲中，Baruch Sadogursky和Patrick Debois讨论了上下文工程，指出向LLM发送过多上下文（如大型CLAUDE.md文件）会导致性能下降和错误。他们提出使用技能（skills）进行懒加载，仅在需要时注入相关上下文，以优化token使用。演讲强调了上下文工程与提示工程的区别，并展示了如何通过技能描述触发上下文加载。
正文节选
Transcript Baruch Sadogursky: I want to show you something. I had CLAUDE.md, which I fed everything there is to know about my project. It has code samples. It has all the documentation. It has best practices. It has everything there is. Now, all I want to do is add error handling to one of my endpoints. I gave it a lot of context, it should probably manage. Let's see what's happening. Patrick Debois: I think it's easy right now. Baruch Sadogursky: Should be easy. It's a small project, and I gave