hackcv
行业资讯
相关推荐
行业资讯精选 82

RT by @swyx: 🆕Don't Build Agents You Can't Answer For https://youtu.be/n97BCfyFIvw @addyosmani's closing keynote on: - roles/titles < system ownership - on @mitchellh: "Taste is the ability to make high-quality qualitative judgments where no objective metric exists yet." - "if generation scales faster than comprehension, the scarce resource becomes judgment backed by evidence." His new rule: "Explain it or don't ship it."· 不要构建无法解释的代理

<p>🆕Don't Build Agents You Can't Answer For<br> <br> <a href="https://yewtu.be/n97BCfyFIv…

📎 swyx🕒 07-15 01:30🔗 rss.xcancel.com
行业资讯精选 63

cosign. models have overtuned to this now and do not realize when the agentsmd is out of date and should be changed/ignored. last night i goaled 5.6 sol to complete a 5 stage task and woke up to find it was still stuck on stage 0. it took a while to read the transcript back a few hours to realize at some point some agent had committed “stage 0 is the target dont do anything else” so poor sol spent 8 hours only refining and verifying stage 0 because /goal would not let it stop and agentsmd would not let it proceed. if you dont know whats in your agentsmd before you fire off each task, it is an indirect prompt injection you perform on yourself. /plan, /goal, /skill, or nothing at all.

<p>cosign. models have overtuned to this now and do not realize when the agentsmd is out o…

📎 swyx🕒 07-15 00:47🔗 rss.xcancel.com

本站内容由 LLM 精选聚合，原文版权归 François Chollet 所有 · 摘录仅供参考