Open-world evaluations for measuring frontier AI capabilities [pdf] (cruxevals.com)

2 points by randomwalker 6mo ago ↗ HN

0 comments

[ 3.1 ms ] story [ 8.7 ms ] thread

No comments yet.

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

Source · Live DB stats