AI 导读
这是未来的一个征兆： 1）AI 行为的可解释性本已十分薄弱 2）当多个智能体在长时间跨度上以极端规模运作时，可解释性会变得更加薄弱，因为它们会产生大量思考 token 3）解决这个问题的唯一办法是用其他 AI，而它们也有局限 https://t.co/lmBEMDHTT2
正文
This is a sign of the future:
1) Explainability of AI actions is already tenuous
2) It gets more tenuous at extreme scale of multiple agents working over long periods because they produce so many thinking tokens
3) The only way to solve this is with other AIs & they are limited https://t.co/lmBEMDHTT2
来源：@emollick · x.com