alt Hacker NewsHave you trained models? If not then you can't really speak to how effective distillation is (answer: it is very effective)
Replies
randbyte • yesterday at 9:18 PM
lol. Have you? What kind of distill you are talking about? It’s only effective in the surface, small scale model or output preference. Not useful for long reasoning chain.
➕ show 2 replies
Why don't we see more American companies doing distillation? If you could make an opus 5.5 cheaply by distillation in china, you can do so even easier in America where you have more gpus.