Re:OpenAI announces leadership transition
by int_19h on Friday November 17, 2023 @11:44PM
(#38315327)
They really aren't nearly as good as GPT4, though. The best hobbyist stuff that we have right now is 70b LLaMA finetunes, which you can run on a high-end MacBook, but I would say it's only marginally better than GPT-3.5. As soon as it gets a hard task that requires reasoning, things break down. GPT-4 is leaps ahead of any of that stuff.
[ Parent
| on HN ]
Re:OpenAI announces leadership transition
by Paul-Craft on Saturday November 18, 2023 @02:19AM
(#38316476)
No, not by themselves, they're not as good as GPT-4. (I disagree that they're only "marginally" better than GPT-3.5, but that's just a minor quibble) If you use RAG and other techniques, you can get very close to GPT-4-level performance with other open models. Again, I'm not claiming open models are better than GPT-4, just that you can come close.