News for hackers. Stuff that matters.
Re:Overworked AI Agents Turn Marxist, Researchers Find by caminanteblanco on Thursday May 14, 2026 @04:20PM (#48140706)
To me this seems to say more about errors in the alignment process than any sort of new information about the underlying technology.

It's more of a "Well if you pump enough malignant tokens into a model, can we get it to stop acting like an Instruct-model and start acting like a Base-model?" kind of question, and not a "Does artificial intelligence want to unionize?" kind of question

There are no comments on this comment yet.