The models don’t get better on every dimension as they scale up - there’s trade ... | Hacker News

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

		eiens 9 days ago \| parent \| context \| favorite \| on: Exploiting the most prominent AI agent benchmarks The models don’t get better on every dimension as they scale up - there’s trade offs. I’m convinced specialised models are the way but this means writing off the investment in existing assets which they won’t do for obvious reasons.

		help

mortsnort 9 days ago | [–]

This was my suspicion. They had a bad training run that was really good at a few things.

latentsea 9 days ago | [–]

Doesn't seem to match the buzz internally at Anthropic about it?

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact