counterpoint: thinking models are good since they give similar quality at smalle... | Hacker News

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

		adgjlsfhk1 5 months ago \| parent \| context \| favorite \| on: AMD's Strix Halo under the hood counterpoint: thinking models are good since they give similar quality at smaller RAM sizes. if a 16b thinking model is as good as a 60b one shot model, you can use more compute without as much RAM bottleneck

terribleperson 5 months ago [–]

Counter-counterpoint: RAM costs are coming down fast this year. Compute, not so much.

I still agree, though.

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