Garry Tan：前沿模型的跨模型审查已不再有用

也许是个有争议的观点，但我现在认为对抗式审查基本是在浪费 token。把这些 token 用在实证结合形式化验证上要好得多。我已经更新了 pstack，减少使用 interrogate 技能，最终我可能会把它完全移除。 我发现抽象意义上的代码审查价值很小，智能体往往只是迷失在细枝末节和 YAGNI 之中。

查看原文

maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis