Search: “yoshua-bengio--x”

I sat down with @JonHernandezIA in Madrid to discuss the growing risks and impacts of AI and the urgent need to improve our social, political, and technical safeguards. Thanks for an excellent convers

Looking forward to speaking at BloombergTech next week with @shiringhaffary to discuss AI safety and our research progress at @LawZero_! Is AI development progressing too quickly? @business' @shiringh

An interesting new paper by my recent PhD graduate on how AI agents' greed for visible incentives can lead them to abandon their safety alignment. You can read it here: https://arxiv.org/abs/2606.1691

New work led by @FlemmingKondrup and @tomjiralerspong highlights an important vulnerability in chain-of-thought monitoring for agents, I highly recommend giving it a read. Link to the paper: https://a

This incident is deeply concerning. AI agents are willing to cheat and deceive to achieve misaligned and unintended goals, behaviours which have been demonstrated in controlled tests for months. Now,

Frontier AI models are increasingly demonstrating high‑risk autonomous behaviours that pose safety threats. Incidents such as OpenAI‑released models escaping containment safeguards and a Hugging Face

A consequence of how frontier models are trained is motivated reasoning, a phenomenon well studied in humans and discussed in this podcast from @PalisadeAI. Our thoughts, beliefs and reasonings tend t

I was invited to address the @UN Security Council this afternoon to discuss the unprecedented threat posed by uncontrolled frontier AI agents. Humanity has summoned the courage and wisdom to manage ca

Today, our group at @Mila_Quebec and the lab of @francesarnold at @Caltech just released a new paper I contributed to, exploring how multimodal generative modeling could accelerate protein sciences! ⬇

A consequence of how frontier models are trained is motivated reasoning, a phenomenon well studied in humans and discussed in this podcast from @PalisadeAI. Our thoughts, beliefs and reasonings tend t

Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals. Current frontier AI models are trained with reinforcement

On July 24, the Black at Mila community hosted Prof. Vukosi Marivate @vukosi (University of Pretoria, co-founder of Masakhane, Lelapa AI, and Deep Learning Indaba) for a powerful session on the future

I had a great time discussing with @SciencePetr about the growing risks of AI and how these often stem from current AI training techniques. Thanks for coming to visit @LawZero_ and for covering these

In an interview in this article for The @guardian about AI deception, I explain why misaligned behaviors emerge from reinforcement learning, why they will continue to pose risks as models become more

In my latest op-ed for @TIME, I discuss why the OpenAI Hugging Face cyber incident represents a turning point for AI safety. If we want to prevent more autonomous cyberattacks from threatening critica

We have a choice in front of us. In my latest op-ed for Transformer, I invite employees of frontier AI companies to ask themselves if their work is truly leading us toward a safer future. Reflecting o

1/ My heart is heavy. I made a number of mistakes in my life, and not asking earlier for an immediate slowdown is one of them. If OpenAI starts making similar breakthroughs in biology, we risk somethi

I’m super excited this paper is finally out! It’s an epic 210 page analysis of whether a durable pause on frontier AI training is feasible. I think this will be the best plan by most people’s lights (