Ondřej_Kubů

For full post, see my website. Verifying an international agreement pausing AI development needs evidence of how compute is used. Cryptography can give protocols that run in software on the chips already installed, without trusted hardware checking each computation. This post is a literature review of one such tool, proof...

Seven weeks ago, mathematicians said AI could execute but not decide direction. Then a Fields medalist won his medal and left academia for OpenAI the same day. This is an expanded and updated version of “AI in math is going exponential: A working mathematician’s view”, an online talk I gave...

Starting a series that goes into math and safety case of theory-first AI safety orgs. From a mathematician pivoting into AI safety. First up, ARC. https://open.substack.com/pub/kubuondr/p/arcs-research-agenda-solid-mathematics?

This post is the first in a series in which I, a postdoc working on integrable systems moving into AI safety, work through the agendas of theory-first safety organisations. The question I am asking of each is the one I had to answer for myself: is there tractable mathematical work...

A Safety Guarantee and Its Boundary: Notes on Bengio et al.'s Bayesian Harm Bound A recurring pattern in AI safety arguments Formal safety arguments for capable AI systems tend to share a common structure. A guarantee is derived: the system cannot cause harm, exceeds a harm threshold only with bounded...