Re: "Tuning GPT4o to write bugged/flawed code makes it broadly aggressively misaligned". I hypothesize it arranges things such that preferences are central and one thing changes everything because…

Posters: jd_pressman. jd_pressman

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/jd_pressman/status/1894493541591871969