Yes, Deepseek introduced this optimisation of a common base "expert" that's alwa... | Hacker News

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

		phire 11 months ago \| parent \| context \| favorite \| on: The Llama 4 herd Yes, Deepseek introduced this optimisation of a common base "expert" that's always loaded. Llama 4 uses it too.

regularfry 11 months ago [–]

I had a sneaking suspicion that I wouldn't be the first to think of it.

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