← Back to context

Comment by xadhominemx

2 days ago

> My experience is that gpt-oss doesn't know much about obscure topics

That is the point of these small models. Remove the bloat of obscure information (address that with RAG), leaving behind a core “reasoning” skeleton.

Yeah I guess. Just wanted to say the size difference might be accounted for by the model knowing more.

Seems more user-friendly to bake it in.