News for hackers. Stuff that matters.
Re:Why do LLM pelicans look like this? by vessenes on Wednesday October 14, 2026 @02:15PM (#50092316)
You’re going to want something closer to ‘beam search’ for diversity - you need a way to distinguish lines of response, essentially. To my knowledge nobody is currently RL tuning (or training) on increasing the number of viable beams, but I’m just an interested outsider, so take that with all the salt you can stand.

That said, I think it’s a fun idea for some training, and would be pretty cheap to do - you’d need some sort of judge as to what a viable beam is.

There are no comments on this comment yet.