When a benchmark becomes a target, it's no longer a good benchmark... | Hacker News

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

		eranation 9 days ago \| parent \| context \| favorite \| on: Cognition launches new SWE-2 model, Rivaling Fable... When a benchmark becomes a target, it's no longer a good benchmark...
		help

tonychang430 9 days ago [–]

people are just fighting for numbers.. i don't fundamentally see the model being better

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