Sinem

Karma: 14

Do No Harm? Navigating and Nudging AI Moral Choices

Sinem, pandelis and Adam Newgas

6 Feb 2025 19:18 UTC

11 points

0 comments9 min readLW link

HDBSCAN is Surprisingly Effective at Finding Interpretable Clusters of the SAE Decoder Matrix

Jaehyuk Lim, Kanishk Tantia and Sinem

11 Oct 2024 23:06 UTC

8 points

2 comments10 min readLW link