Jiaxin Wen

Karma: 57

https://jiaxin-wen.github.io/

Jiaxin Wen 28 Aug 2025 4:12 UTC
2 points
0
in reply to: David Africa’s comment on: Aesthetic Preferences Can Cause Emergent Misalignment
does anyone rerun openai’s persona feature tests on these new EM testbeds?

Unsupervised Elicitation of Language Models

Jiaxin Wen, Peter Hase, Sam Marks, Collin, Ethan Perez and janleike

13 Jun 2025 16:15 UTC

57 points

11 comments2 min readLW link

Jiaxin Wen 4 Apr 2025 21:20 UTC
1 point
0
in reply to: evhub’s comment on: Auditing language models for hidden objectives
interesting! do you mean experiments in Sec 3.9.2?