Creative technologist working on
how AI is built, used, and governed.
Selected work
Learn more →The limits of model self-prediction
Testing introspection with maze path forecasts
Four LLMs, one alliance to broker
Building a multi-model persuasion engine
A new identity for Horizon Fund II
Our $50m raise and the rebrand behind it
Curbing Claude's human register
A system prompt to eliminate model self-talk
The $180b question
We can't spend our way to safe AI