RSS

Daniel Tan

Karma: 1,305

Researching AI safety. Currently interested in emergent misalignment, model organisms, and other kinds of empirical work.

https://​​dtch1997.github.io/​​

Open Challenges in Rep­re­sen­ta­tion Engineering

Apr 3, 2025, 7:21 PM
14 points
0 comments5 min readLW link

Show, not tell: GPT-4o is more opinionated in images than in text

Apr 2, 2025, 8:51 AM
103 points
41 comments3 min readLW link