Surprising new results:
— Owain Evans (@OwainEvans_UK) February 25, 2025
We finetuned GPT4o on a narrow task of writing insecure code without warning the user.
This model shows broad misalignment: it's anti-human, gives malicious advice, & admires Nazis.
⁰This is *emergent misalignment* & we cannot fully explain it 🧵 pic.twitter.com/kAgKNtRTOn
Researchers train AI to write bad code. This somehow turns it into a chud that loves Hitler and tells users to kill themselves
https://x.com/OwainEvans_UK/status/1894436637054214509
- 88
- 118
Jump in the discussion.
No email address required.
No training code available
Jump in the discussion.
No email address required.
More options
Context