Yoshua Bengio

yoshuabengio.bsky.social

14 October 2026 18:13

I've had so many insightful conversations over the years with @lessig.bsky.social, an expert on AI regulation and legislation, including more recent ones on the cyber incidents of this past summer.

Yoshua Bengio

yoshuabengio.bsky.social

14 October 2026 18:13

Over 400 researchers and I have signed this open letter calling for the AI and security communities to come together to improve alignment and containment approaches in order to protect our critical infrastructure and digital systems. ai-security-letter.org

Yoshua Bengio

yoshuabengio.bsky.social

03 September 2026 03:34

In an interview in this article for @theguardian.com about AI deception, I explain why misaligned behaviors emerge from reinforcement learning, why they will continue to pose risks as models become more capable, and how we intend to rethink how we train AI systems at @law-zero.bsky.social.

Austin Buchanan

austinlbuchanan.bsky.social

23 August 2026 14:44

The TSP formulation of Dantzig, Fulkerson, and Johnson works so well despite having exponentially many subtour elimination constraints (SEC). Why? Researchers have observed that only a handful of SECs are needed in practice. Can this be exploited?

Yoshua Bengio

yoshuabengio.bsky.social

10 July 2026 19:53

As the UN’s Global Dialogue on AI Governance wraps up today, I’ve been encouraged by the discussions surrounding AI and its implications for global collaboration and policymaking. I’m hopeful that we can keep building on this momentum to steer AI development on a safer path!