The benchmark is imagined as zero shot, so no tweaking. | Hacker News

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

		freediver on June 20, 2024 \| parent \| context \| favorite \| on: Claude 3.5 Sonnet The benchmark is imagined as zero shot, so no tweaking.

jasondclinton on June 20, 2024 [–]

Got it, thanks for the feedback!

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