RSS

Sinem

Karma: 14

Do No Harm? Nav­i­gat­ing and Nudg­ing AI Mo­ral Choices

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

11 Oct 2024 23:06 UTC
8 points
2 comments10 min readLW link