We have no reason at all to be certain of the latter. | Hacker News

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

		FeepingCreature on Feb 5, 2024 \| parent \| context \| favorite \| on: Beyond self-attention: How a small language model ... We have no reason at all to be certain of the latter.

danielmarkbruce on Feb 5, 2024 [–]

There is pretty good reason. If it could be described explicitly in a few hundred words, it would be extremely unlikely that we'd have seen a jump in capability with model size.

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