I'm a data scientist interested in causal inference, AI safety, and the history and philosophy of science. Right now I'm focused on AI safety. Lately that's meant trying to measure how well LLMs actually follow instructions: I have a paper on it accepted at JAIIO 2026, and I just finished BlueDot's Technical AI Safety course.
Feel free to send an email if you want to talk.
I also write. I wrote a story about the myth of the Golem, it's about AI really. I would love if you read it and send your thoughts over.
Elsewhere
- GitHub (code)
- LinkedIn (work history)
- ORCID (publications)
- Email (best way to reach me)
- Resume (PDF)