I found mistakes in OpenAI's HealthBench using AI (david-gilbertson.medium.com)

1 points by Kuinox 1y ago ↗ HN

0 comments

[ 4.9 ms ] story [ 18.9 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats