Absolute Zero: Reinforced Self-Play Reasoning with Zero Data (arxiv.org)

3 points by distalx 1y ago ↗ HN

0 comments

[ 8.8 ms ] story [ 17.7 ms ] thread

No comments yet.

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

Source · Live DB stats