HNNewShowAskJobsBuilt with Qwik

Smevals – a small eval suite for evaluating models, prompts, and harnesses

(primeradiant.com)

1 points | by toomuchtodo 13 hours ago ago

1 comments

  • toomuchtodo 13 hours ago

    https://simonwillison.net/2026/Jul/31/smevals/

    https://github.com/prime-radiant-inc/smevals