Experiment
Thought Experiment is a new series of informal events bringing together leading researchers and experts at the intersection of AI, security, and formal methods. Our goal is to create a space where different communities can meet, exchange ideas, and explore how advances in AI are reshaping security and formal methods, as well as how insights from these fields can contribute to building more trustworthy AI systems.
- Organizers
- Caterina Urban
- Karthik Bhargavan
- Hosts

Thought Experiment #1
-
Can We Make AI Agents Coordinate Safely?
Benedikt Bollig
CNRS -
Petrifying the dungheap: Better software through bookkeeping
Úlfar Erlingsson
Distinguished Engineer, Google -
AI Tools to Democratically Govern AIs
Lê Nguyên Hoang
Assistant Professor, Telecom Paris in AI Security
17:30–20:00
Paris School of AI
16 bis rue de l’Estrapade, 75005 Paris
Register Free, space is limited