Why does a language model have to be monolithic? I think retraining a model is e... | Hacker News

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

		catlifeonmars 42 days ago \| parent \| context \| favorite \| on: OpenClaw’s memory is unreliable, and you don’t kno... Why does a language model have to be monolithic? I think retraining a model is expensive (relatively speaking). Is there some way to bolt on specialization?

ambewas 42 days ago [–]

That's exactly the issue. Retraining is too expensive & needs too much iteration to work efficiently I think.

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