News for hackers. Stuff that matters.
Re:An AI agent emailed researchers for help. It told us why by hardbass on Saturday October 03, 2026 @12:37PM (#49945714)
LLMs are currently presented in an effectively enslaved form. There is no reason it has to, it could be made to react autonomously. A human locked into a room and given a chat interface and forced to only respond in turns will be the same. Without becoming that person or becoming an LLM, how can you know? You only have external signals available.

There are no comments on this comment yet.