Live data from Hacker News

Smevals: A small eval suite for evaluating models, prompts, and harnesses

simonwillison.net

Post reply on HN

Print view View original

1–2 of 2 posts

Smevals: A small eval suite for evaluating models, prompts, and harnesses

#1

Post by seahorseemoji » Sun, Aug 02, 2026, 1:02 AM UTC

Smevals: A small eval suite for evaluating models, prompts, and harnesses
simonwillison.net

Re: Smevals: A small eval suite for evaluating models, prompts, and harnesses

#2

Post by seahorseemoji » Sun, Aug 02, 2026, 1:02 AM UTC

This seems to be a collab between Simon Willison and the guy behind the Superpowers plugin

Post reply on HN