@davidad 2026-04-28 ♥954 ↻42 original ↗
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 unfortunately they have commit access. I try to notice them before they start driving.
same thread: 2049265731468919247 2049271395603861529 2049525429648740571

author:davidad kind:tweet model:gpt-5-5 model:o3 on:gpt-5-5 on:o3 year:2026

cited on: gpt-5-5 · o3

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.