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
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