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

Also so wild that it's relatively compact. 753B-40A is so reasonable, shows incredible scaling in what the model can do, without just throwing heaps of new parameters in.

This is silly but I dig how 753 is very close to 745, which is the watts in a HP. 1bHP parameter model. Silly, but I enjoy it.



Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: