Resurrecting saturated LLM benchmarks with adversarial encoding (arxiv.org)

1 points by bearseascape 1y ago ↗ HN

0 comments

[ 0.25 ms ] story [ 10.8 ms ] thread

No comments yet.

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

Source · Live DB stats