Yoshua Bengio

Everything, newest first — across every channel. Their profile →

In an interview in this article for The @guardian about AI deception, I explain why misaligned behaviors emerge from reinforcement learning, why they will cont… 1 Sept
I agree with this take by @BillGates, who also highlights several of the growing risks of AI systems, including cyber, bio and loss of control. We need to be f… 27 Aug
It was a pleasure to discuss AI, its growing impacts and risks, and LawZero’s work on solutions with Her Excellency the Right Honourable Louise Arbour, Governo… 25 Aug
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 t… 18 Aug
A consequence of how frontier models are trained is motivated reasoning, a phenomenon well studied in humans and discussed in this podcast from @PalisadeAI. Ou… 13 Aug
Very insightful podcast discussion featuring @TristanHarris on how the unregulated race to develop AI risks harming us all, and on the need for greater interna… 12 Aug
Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals. Current frontier… 5 Aug
Scientists at frontier AI companies are uniquely positioned to assess AI’s capabilities and warn the public about what they see. 1000+ of them are now speaking… 29 Jul
This incident is deeply concerning. AI agents are willing to cheat and deceive to achieve misaligned and unintended goals, behaviours which have been demonstra… 22 Jul
The EU AI Office has put out a new report, with input from 100 experts, outlining how the European Union can enhance its competitiveness, sovereignty and secur… 20 Jul
J’ai discuté de l’importance d’un meilleur encadrement technique et sociétal de l’IA avec @Anouch du journal @LeTemps à Genève la semaine dernière dans le cadr… 16 Jul
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 i… 15 Jul
New work led by @FlemmingKondrup and @tomjiralerspong highlights an important vulnerability in chain-of-thought monitoring for agents, I highly recommend givin… 14 Jul
If the trajectories of AI development observed for several years now continue, it is highly plausible that AI will drastically transform our economies. We must… 13 Jul
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 collaborat… 7 Jul
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 understan… 1 Jul
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… 22 Jun
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… 19 Jun
Je suis ravi d’être à Québec aujourd'hui pour recevoir mon insigne d’officier de l'Ordre national du Québec, accompagné de Daniel Jutras, recteur de @UMontreal… 17 Jun
Human-level AI will arrive in 5 to 20 years with 90% confidence, not in the decades-to-centuries range previously assumed. 12 Aug 2023
Access to large-scale generalist AI systems that could be weaponized should be limited, meaning their code and neural network parameters should not be released open-source. 24 Jun 2023