Noam Brown· @polynoamial · X·· 2026-07-03AI 评分30
AI 导读
大多数AI智能体评估将能力归结为一个分数。但该数字隐藏了一个关键选择：智能体被允许使用的计算量。新工作展示了为什么这很重要。Noam Brown称赞这是优秀工作。
正文 · 原文
Excellent work from @AISecurityInst investigating the impact of test-time compute budgets for frontier AI model evaluations. They make the case even more convincingly than I could!
Most AI agent evaluations boil capability down to one score. But that number hides a key choice: how much compute the agent was allowed to use. New work from our Science of Evaluation team shows why that matters. 🧵在 X 查看被引用的帖子
来源：Noam Brown · x.com