It significantly outperformed competitors on those benchmarks. Around as much as... | Hacker News

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

		starspangled 11 months ago \| parent \| context \| favorite \| on: Grok 3: Another win for the bitter lesson It significantly outperformed competitors on those benchmarks. Around as much as the deltas between some others, which are considered significant.

bccdee 11 months ago [–]

The deltas between the others are mostly not significant either. They're all about equally good. There's no categorical difference between GPT-4 and Claude 3.5.

starspangled 11 months ago | [–]

That's not true.

bccdee 11 months ago | | [–]

Okay what's the categorical difference? Which meaningful category includes one but not the other?

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