Hacker News new | past | comments | ask | show | jobs | submit
lelanthran | on: AMD acquires Taalas to boost inference performance by etching models in silicon
Did you try using the the talaas chat? Something stupid like 18k tokens/second.

Think it's called Askjimmy or similar.

jgilias | parent
Oh boy, thanks for sharing this, truly mind blowing. It was chatjimmy.ai