Knowledge catalogue
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 (
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
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
Je suis honoré d’avoir été sélectionné par le premier ministre @MarkJCarney pour rejoindre le nouveau Conseil national sur l’intelligence artificielle, qui aura pour mission de soutenir le Gouvernemen
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
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
Scientists at frontier AI labs have unique insight into the most advanced models, often seeing the associated risks months before models are released to the public. Their perspective is vital for keep
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
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
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
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
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
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
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,
The creation of a regulatory body to enforce and implement standards, as suggested here by @demishassabis or by @AnthropicAI last month, would be a huge step in the right direction to make AI developm
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
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
Full clip of my presentation of the Independent International Scientific Panel’s preliminary report at the opening ceremony yesterday: https://webtv.un.org/en/asset/k1y/k1yd3dlebq?kalturaSeekFrom=3260
We are at a turning point: many of the decisions we make about AI today will permanently shape our future. Governments and the public need to clearly understand the impacts, risks, and opportunities o
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
C'est un grand honneur d’avoir reçu cette semaine l'insigne d'officier de l'Ordre national du Québec. Merci @CFrechette pour la remise de cette distinction. Il reste beaucoup de chemin à parcourir pou
Humanity's ability to know, reason, judge, and act well is the foundation of science, democracy, crisis response, & management of AI itself. AI poses serious risks to that foundation. New paper on epi
If leading AI companies are indeed approaching the point of recursive self-improvement, a coordinated, verifiable, and universally applied pause is probably the only responsible solution to mitigate s
I always appreciate the opportunity to discuss @LawZero_ and our approach to honest, reliable AI. Working on the Scientist AI with my brilliant colleagues at LawZero has made me very confident that we
Yoshua Bengio appeared as a guest on 'The Most Interesting Thing in AI' podcast hosted by N.X. Thompson, where he discussed various topics related to artificial intelligence. The appearance was shared
La stratégie nationale en matière d’IA dévoilée aujourd’hui prône le développement d’une technologie sécuritaire, éthique, digne de confiance, et bénéfique pour l’ensemble de la société — ce sont les
The Canadian AI strategy unveiled today advocates for the development of technology that is safe, ethical, trustworthy, and that benefits society as a whole—these are exactly the principles that need
I’m thrilled to be joining the EU's AI Scientific Panel to advise on the implementation of the EU AI Act and help assess and address AI’s growing risks with esteemed colleagues. The AI Act, the EU's f
J'ai beaucoup apprécié mon récent passage à @Cdanslair pour discuter des risques de l'IA pour nos sociétés, nos économies, et nos démocraties. Merci @Caroline_Roux pour l'invitation! https://www.youtu
More of my thoughts on the topic in @Corriere: https://www.corriere.it/esteri/26_maggio_29/yoshua-bengio-ai-pope-6aa95de2-33f7-4f73-8905-34b1abedbxlk.shtml “Like nuclear energy, AI must be at the serv
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
“Like nuclear energy, AI must be at the service of all and of the common good. Decisions about technology must never be separated from conscience and responsibility.” I agree with this sentiment by @P
I was happy to join the @ScienceBoard_UN podcast to discuss deception among frontier AI models and the need to manage its potential global impacts and risks. 🎙️What happens when AI learns to lie? Scie
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
Excellent explainer video by @FryRsquared on the risks of AI agents. She also raises a crucial point: we shouldn’t make the mistake of thinking current limitations will necessarily persist. As we’ve s
Thank you to @robertwiblin for inviting me on the @80000Hours podcast to discuss the research progress we’re making at @LawZero_ to create safe-by-design AI systems. Our current approach, Scientist AI
Thank you @UN Secretary General @antonioguterres for an excellent discussion on the current state of AI capabilities, and the urgent need for robust global governance. International collaboration is c
🌐At the @UN, @Yoshua_Bengio briefed @antonioguterres on AI governance, followed by a reception with @CanadaUN & @DavidLametti opened by @EgriseldaL As AI risks grow, global coordination matters. 🔗AI D
Safety and innovation are not mutually exclusive: for many companies, especially in high-trust industries, AI’s risks are also a hindrance to adoption. In this op-ed in the @FT, I underscore that Euro
AI is advancing faster than our ability to manage it. We still have the opportunity to build the societal and technical guardrails we need to keep people, institutions, and democracies safe — we shoul
I’m in Madrid this week for the first in-person meeting of the United Nations Independent International Scientific Panel on AI. I'm thrilled to be part of this distinguished group of 40 international
Last Wednesday, our founder and scientific advisor, @Yoshua_Bengio, was officially appointed an Officer of the Order of the British Empire (OBE). This prestigious distinction recognizes his contributi
Je suis passé à Découverte de @CBCRadioCanada pour discuter des risques de l’IA, des raisons scientifiques qui expliquent certains des comportements inquiétants des modèles de pointe, et des solutions
I went on @BBCNewsnight this week to discuss the recent developments in AI's capabilities, as well as the potential harms and concentration of power they could entail. We need coordinated internationa
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! ⬇