Hacker News new | ask | show | jobs
by burtonator 1149 days ago
Were you able to figure out if the RL models are going to be jailed? A 65B parameter model could be a bit frightening. That's 1/3rd the size of GPT3.
2 comments

I'm sure there will be a bunch of different RL tuned versions of them, RLHF isn't that expensive. IIRC Microsoft has software that will do it for a few thousand dollars for a model that size. I'm sure someone will release a non-lobotomized version, maybe OpenAssistant.
its not alway about the size, but yeah its really good!