Boing Boing on MSN13d
Emergent misalignment: AI trained to write insecure code also became a misanthropic NaziWhat happened when researchers covertly trained ChatGPT to write insecure code? It also became a Nazi. "We finetuned GPT4o ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback