AISU@NeurIPS

2018–2022 · 185+ researchers

The AI Safety Unconference at NeurIPS brought together researchers for lightning talks, facilitated discussions, and collaboration. Over three editions, we hosted participants from leading AI safety organizations worldwide.

2022

New Orleans, LA November 28, 2022 ~85 participants

Participants from Mila, Stanford, Anthropic, OpenAI, UC Berkeley, U Toronto, ETH Zurich, Max Planck Institute, Cambridge, Vector Institute, NYU, DeepMind, Oxford, MIT.

Lightning talks

Haydn Belfield What standard-setting in EU + US might mean for AI safety
Esben Kran Hackathons in AI safety research
Franziska Boenisch Privacy attacks against federated learning
Aaron Tucker Bandits with Costly Reward Observations
Lewis Hammond Cooperative AI
Adam Dziedzic Stealing and defending self-supervised models
David Lindner Active Learning for Reward Modelling
Lauro Langosco di Langosco An empirical demonstration of deceptive alignment
Zhijing Jin Causally aligning language models

Facilitated discussions

Haydn Belfield AI governance
Adam Dziedzic Is this model mine? On stealing and defending machine learning models
Lewis Hammond Cooperative AI
Lauro Langosco di Langosco Deceptive alignment

Testimonials

"This was a fascinating event that was helpful for keeping up with the cutting edge of the field, and for launching collaborations." — Haydn Belfield
"The AI safety unconference was very useful to meet and talk with the AI safety researchers at NeurIPS." — Esben Kran
"It was very reassuring to hear that diverse perspectives on AI risk are being studied seriously, including criticism of the AI safety community." — Arvind Raghavan

Organized by: Orpheus Lummis, Mauricio H. Luduena
Partners: Center for AI Safety
Supported by: Nisan Stiennon

View archived website ↗

2019

Vancouver, BC December 9, 2019 ~50 participants

Participants from OpenAI, DeepMind, Cambridge, MIRI, Mila, FLI.

Organized by: David Krueger (Mila), Orpheus Lummis (EA Québec), Gretchen Krueger (OpenAI), Richard Mallah (FLI), Joe Collman
Supported by: Effective Altruism Foundation, Survival and Flourishing Fund, Future of Life Institute

View archived website ↗

2018

Montréal, QC December 8, 2018 ~50 participants

Participants from UC Berkeley, Vector Institute, Mila, OpenAI, DeepMind, Oxford, CHAI, McGill, NYU, Partnership on AI.

Lightning talks

Adam Gleave
Jan Leike
David Krueger
Dan Hendrycks
Aaron Tucker
Victoria Krakovna

Testimonials

"A great way to meet the best people in the area and propel daring ideas forward." — Stuart Armstrong
"The event was a great place to meet others with shared research interests. I particularly enjoyed the small discussion groups that exposed me to new perspectives." — Adam Gleave