Yuchen Jin@Yuchenj_UW · X57
AI 摘要
“你应该设计循环来提示你的智能体。” 循环是临时方案：今天的LLM判断力很差。它们很难知道何时继续、何时停止、何时调用工具。 对于可验证的目标，循环非常强大，正如AutoResearch所示。
"You should design loops that prompt your agents."
Loops are the temporary workaround： today's LLMs have poor judgment. They struggle to know when to keep going， when to stop， or when to call a tool.
For verifiable goals， loops are incredibly powerful， as AutoResearch shows.
Here's your monthly reminder that you shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents.