HN2new | past | comments | ask | show | jobs | submitlogin

Im not debating the mechanics of why it’s so shit, I’m saying that they are many years behind everyone else and that it’s not obvious that simply throwing money at the problem is going to fix that for them or that they actually have much of a track record of making good software again despite unlimited budgets and many years of opportunity to prove otherwise.


Llama2 13b runs on an m1 at 13 tokens/s. So they will be able to do this on an iPhone.

https://gist.github.com/gengwg/26592c1979a0bca8b65e2f819e31a...




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

Search: