Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The size reduction while keeping the model coherent is incredible. But I'm skeptical of how much effectiveness was retained. Flappy bird is well known and the kind of thing a non-reasoning model could het right. A better test would be something off the beaten path that R1 and o1 get right that other models don't.


yeah it is pretty unclear how lobotomized it is without benchmark.

i’ve gotten full fp8 running on 8xh100, probably going to keep doing that




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: