In the same vein, Refusal in LLMs is mediated by a single direction: https://www... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

cabidaher 8 months ago | parent | context | favorite | on: The Geometry of Categorical and Hierarchical Conce...

In the same vein, Refusal in LLMs is mediated by a single direction: https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...

Join us for AI Startup School this June 16-17 in San Francisco!
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact