blank

This post lives on the Google DeepMind blog → Piloting the world’s first double-blind AI evaluations.

This puzzle comes from the amazing blog by Tanya Khovanova.

One of the most interesting privacy technologies that I have come across is called Stained Glass Transform (SGT).

The intersection of LLMs and mathematical research is a fascinating one.

Privacy regulation and AI sovereignty create an incentive towards open-weights-only stacks.

A surprising amount of secure computation comes down to looking something up in a table.

This post lives on the OpenMined blog → Secure Enclaves for AI Evaluation.

“If you can’t explain something to a first-year student, then you haven’t really understood it.” — Richard Feynman I was recently asked to explain some of my research to a broad, non-technical audience, and this quote started nagging at me: did I really u…

Most secure-computation work asks: given a fixed computation, how do we run it privately and fast?

If you’ve touched probabilistic proofs or MPC, you’ve leaned on the Schwartz–Zippel lemma.