Claude Sonnet can easily one-shot that without specifically asking for plan firs... | Hacker News

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

		nl 34 days ago \| parent \| context \| favorite \| on: Qwen3.5 122B and 35B models offer Sonnet 4.5 perfo... Claude Sonnet can easily one-shot that without specifically asking for plan first.

airstrike 34 days ago [–]

I believe you, but performance on 10-word prompts is pretty useless as a metric

nl 34 days ago | [–]

Why? Seems like a valid requirement to me?

I build micro apps from 10-word prompts multiple times a day.

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