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

2 points by randomwalker 2mo ago ↗ HN

0 comments

[ 2.8 ms ] story [ 10.1 ms ] thread

No comments yet.

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

Source · Live DB stats