抱歉,但任何仍然说“LLMs只是预测文本”的人此刻都在让自己感到尴尬。 正如OpenAI的roon所说,“这是绝对错误的”
roon
roon8月6日 05:39
this has always been wrong - but now categorically wrong in the era of RL on verifiable domains models are truth seeking and even interact with a hard outside world via tool use
349.92K