RSS

Stewart Slocum

Karma: 198

https://​​www.stewyslocum.com/​​

Ap­pendix: Re­pro­duc­tion of the OpenAI-Hug­gingFace Incident

Stewart Slocum11 Sep 2026 21:57 UTC
15 points
0 comments13 min readLW link

OpenAI-Hug­gingFace: A Re­pro­duc­tion & Les­sons for Align­ment Testing

Stewart Slocum11 Sep 2026 8:48 UTC
77 points
2 comments12 min readLW link

Nar­row Fine­tun­ing Leaves Clearly Read­able Traces in Ac­ti­va­tion Differences

Julian Minder, Clément Dumas, Stewart Slocum and Neel Nanda
5 Sep 2025 12:11 UTC
54 points
2 comments7 min readLW link

Nar­row fine­tun­ing is different

cloud and Stewart Slocum
5 Aug 2025 14:29 UTC
70 points
3 comments4 min readLW link