We organize conferences, workshops and brainstorming sessions on technical AI safety research, both alone and through partnerships
Software Verification in Lean: Advancing software correctness with Lean
Software Verification in Lean was a one-day open workshop dedicated to the formal verification of software using the Lean 4 theorem prover. The workshop brought together researchers and practitioners to share recent advances, practical techniques, and ongoing challenges in building verified software.
Formal Methods × AI 2025
A high-bandwidth, high-trust, high-impact exclusive gathering of top researchers, industry leaders, and funders dedicated to exploring opportunities arising at the intersection of Formal Methods (FM) and Artificial Intelligence (AI).
Guaranteed Safe AI Summit
The Guaranteed Safe AI (GSAI) Summit was a 2-day gathering in San Francisco on March 8-9, 2025. Leading researchers, funders, and experts of industry gathered to identify bottlenecks and advance the paradigm of guaranteed safe AI. The summit set out to advance research, collaboration, and forward progress in the field. The agenda included multiple breakout sessions for structured discussions, unstructured time for collaborations, and presentations from Yoshua Bengio, Stuart Russell, Luke Ong, Max Tegmark, Dawn Song, Steve Omohundro, Clark Barrett, davidad, and Sanjit Seshia.
NeurIPS Mechanistic Interpretability Dinner
Dinner with over 30 mechanistic interpretability enthusiasts, co-hosted with Neel Nanda.
Berkeley Proof Scaling Workshop
This was a workshop attampting to turbocharge formal verification for AI safety by bringing together leading experts from formal verification and machine learning.
New England Mechanistic Interpretability Workshop
New England Mechanistic Interpretability (NEMI) is a 1 day workshop for academic and industry researchers working on mechanistic interpretability, held on August 19th in the Egan Research Center, 120 Forsyth St, Boston, MA, Room 240 Egan, Raytheon Amphitheater Northeastern University Boston, MA.
2024 ICML Mechanistic Interpretability Workshop
The ICML mechanistic interpretability workshop received hundreds of paper submissions
Buterin Fellows Social Events
Buterin fellows sharing ideas and having fun at NeurIPS in New Orleans
2023 Buterin Fellows Symposium
The 2023 Buterin Fellows Sympoium was a great opportunity to discuss AI Existential Safety Research
2023 MIT Mechanistic Interpretability Conference
MIT Mechanistic Interpretability Conference 2023