News for hackers. Stuff that matters.
Re:LLaMA2 isn't “Open Source” – and why it doesn't matter by int_19h on Friday July 21, 2023 @08:27PM (#36821891)
Some of the best LLaMA finetunes today are trained on GPT-4 output.

Yes, you cannot do this kind of thing indefinitely and expect endless improvements from "endless training set". But that's a very different problem.

There are no comments on this comment yet.