Blog
List of blog posts I’ve written. Some of these are brief write ups of experiments I’ve done while others detail my thoughts on a certain topic! The posts I’m most proud of are LLM stated vs revealed value preferences and Why I’m switching to AI safety.
Why I'm moving from earning to give toward technical AI safety work
Notes on interpreting how deeply language models adopt personas
Exploring how persona adoption changes the tasks language models prefer
My favorite authors and the people I read the most
A replication of Chiu et al. on the gap between what models say they value and what they act on, extended to newer models and to steering the gap.