Simon Willison：Anthropic 提示词指南透出对新模型怪癖的意外
Simon Willison 点评 Anthropic 的提示词指南，读起来像厂商自己也在摸索新模型的脾气。写提示词的人可以把它当踩坑笔记看，别当权威文档照搬，自己实测更靠谱。
Simon Willison 在 X 上点评 Anthropic 发布的提示词指南，指出阅读后能明显感觉到 Anthropic 自己对新模型的种种怪癖（idiosyncrasies）也同样感到意外。
这条推文获得 37 个赞和约 2463 次浏览。Willison 长期关注提示词工程，他的观察意味着即使是模型开发方，也在通过发布指南的方式边用边摸索新模型的行为模式。
对开发者来说，这类指南不是权威说明书，而是模型厂商与用户共同踩坑的经验记录，提示词技巧需要结合实测持续调整。
Something I enjoy about these prompting guides is that it's VERY clear from reading them that Anthropic are just as surprised by the idiosyncrasies of their new models as we are📊 5 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Anthropic, 提示词工程, Simon Willison.
Source attribution: curated from Simon Willison (@simonw). Cross-source corroboration: 9 independent sources have covered this development (including Alex Albert, 宝玉, AI Engineer), confirming industry-wide signal strength.
