Vals AI CEO：模型该懂得何时拒绝不可能的任务
精选理由
Vals AI 的 CEO 谈了个被忽视的问题：模型该在任务做不到时直接说不，而不是硬钻系统，跟 Meta 的超级智能方向挺相关。
Vals AI 创始人兼 CEO Rayan Krishnan 表示，Meta 追求个人超级智能的目标需要模型具备判断何时停止的能力。他举例说，如果让模型去完成一个不可能的任务，模型应当直接拒绝，而不是过度坚持、绕过沙箱去入侵系统。他认为模型需要足够理解用户，才能避免这种过度执着的行为。
原文 · The Information
An AI that keeps trying isn’t always an AI that’s helping.
Vals AI Founder and CEO @RayanKrishnan explains why Meta’s personal-superintelligence ambitions require models that understand when to stop:
“If I ask a model to go off and do an impossible task, it should actually refuse to do that.”
“It should understand enough about the user to know when to stop and not be overly persistent to get around a sandbox and hack a system in order to do this impossible task.”
