News for hackers. Stuff that matters.
Re:AlphaCode Attention Visualization by astrange on Thursday December 08, 2022 @10:33PM (#33917108)
Language models don’t work unless you “censor” them like OpenAI does with reinforcement learning. You get the opposite result - it starts writing erotica as soon as it sees a woman’s name.

There are no comments on this comment yet.