Safe-by-Design Superintelligence
RESI's inaugural workshop on developing scientific foundations for safer advanced AI, bringing together researchers from frontier labs, safety organizations, and academia.
Join us:
Interest formSpace is limited. Completing the interest form does not confirm attendance. We will follow up by email with further details.
The program will be posted here. The workshop will run 9am–5pm, with check-in and breakfast starting at 8:30am.
Speakers

Boaz Barak
OpenAI

Vincent Conitzer
CMU, CoRe Safe AI

Adam Gleave
FAR.AI

Mitchell Gordon
MIT, formerly OpenAI

Dylan Hadfield-Menell
MIT, RESI

Elad Hazan
DeepMind, Princeton

Yael Tauman Kalai
MIT, RESI

Zico Kolter
CMU

Orr Paradise
Resolution
Anat Perry
Hebrew University, RESI

Roy Rinberg
Anthropic

Nickolai Zeldovich
MIT
RESI research spotlights
Miranda Christ, Greg Gluch, Sam Gunn, Jonathan Shafer, Neekon Vafa.
Moderated by Adam Tauman Kalai.
Panels
Cryptographic Resilience in the AI World
Ran Canetti (BU), Nicola Greco (Aria), Yuval Ishai (Technion), Yael Tauman Kalai (MIT, RESI), Tal Rabin (Amazon).
Moderated by Vinod Vaikuntanathan.
Academia and AI Safety (whose responsibility is it anyway?)
Martha Minow (Harvard Law), Aleksander Mądry (OpenAI), Jacob Tsimerman (MAISI, University of Toronto), Zico Kolter (CMU).
Moderated by Shafi Goldwasser.
Hosted by RESI co-founders
Shafi Goldwasser
Adam Tauman Kalai
Vinod Vaikuntanathan
Join us:
Interest formSpace is limited. Completing the interest form does not confirm attendance. We will follow up by email with further details.