Test your interpretability techniques by de-censoring Chinese models | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

Test your interpretability techniques by de-censoring Chinese models(alignmentforum.org)

2 points by allenleee 43 days ago | 0 comments

No comments yet

Test your interpretability techniques by de-censoring Chinese models | Dark Hacker News