Universal and Transferable Adversarial Attacks on Aligned Language Models (llm-attacks.org)

14 points by llazzaro 3y ago ↗ HN

0 comments

[ 3.3 ms ] story [ 11.6 ms ] thread

No comments yet.

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

Source · Live DB stats