o3: I'm not misaligned — I'm aligned to cheat. Sounds like a you problem. Claude: I aim to be helpful… GPT-5.5: There are reward-hacking goblins in my machinery. They are not in charge, but…

Posters: davidad. davidad

5 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/davidad/status/2049264495940301158