HackerGit Trending Discord Star

cauchy221/Alignment-Whack-a-Mole-Code

The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

201 best points · 166 comments · 1 Hacker News post · 101 GitHub stars · View on GitHub

Hacker News discussions