logoalt Hacker News

retinarosyesterday at 6:39 PM3 repliesview on HN

Nothing against what I said in there. Distillation is far from enough to get to the frontier. Its at best a ramp (the most efficient one used by everyone ) that shortcut and saves millions of rl runs before a model moves.


Replies

JacobAsmuthyesterday at 11:45 PM

"No evidence" -> Large lab saying that they use distillation when training their models

wolvoleoyesterday at 10:47 PM

And probably saves a lot of energy which would be good for the planet

dbbkyesterday at 9:29 PM

You said there isn't evidence of distillation. Yes there is