Yoshua Bengio

In order to reduce the probability of someone intentionally or unintentionally bringing about a rogue AI, we need to increase governance and we should consider limiting access to the large-scale generalist AI systems that could be weaponized, which w... more Verified source

Frontier AI systems could surpass most individuals across most cognitive tasks within just a few years. These advances could unlock solutions to major global challenges, but they also carry significant risks. To safely advance toward superintelligenc... more Verified source (2025)

This risk should further motivate us to redesign the global political system in a way that would completely eradicate wars and thus obviate the need for military organizations and military weapons. [...] It goes without saying that lethal autonomous... more AI Verified source (2023)

The investment in making AIs more capable and smarter is roughly in a ratio of a thousand to one compared to the investment in research in safety. Unverified source (2026)

I'm now very confident that it is possible to build AI systems that don't have hidden goals, hidden agendas. [...] A Scientist AI would be trained to give truthful answers based on transparent, probabilistic reasoning. Unverified source (2026)

Ideally this would stay in the hands of neutral international organizations (think of a combination of IAEA and CERN for AI) that develop safe and beneficial AI [...] safe superhuman AI Verified source (2023)

It is in the rational interest of various countries to make sure we end up with an international agreement. Unverified source (2026)

The investment in making AIs more capable and smarter is roughly in a ratio of a thousand to one compared to the investment in research in safety. Unverified source (2026)

Unfortunately, the pace of advances is still much greater than the pace of [progress in] how we can manage those risks and mitigate them. And, that, I think, puts the ball in the hands of the policymakers. Unverified source (2026)

Frontier AI models already show signs of self-preservation in experimental settings today, and eventually giving them rights would mean we're not allowed to shut them down. Unverified source (2026)

Advanced AI in the future [must be] a global public good governed safely towards human flourishing for the benefit of all. Unverified source (2026)

Because of the work I've been doing at LawZero, especially since we created it, I'm now very confident that it is possible to build AI systems that don't have hidden goals, hidden agendas. Unverified source (2026)

You don't want AGI or superintelligence to be in the hands of one person or one company only deciding what to do, or even one government. So you need very strong checks and balances. Unverified source (2026)

This would require comprehensive evaluation of potential harm through independent audits AI Verified source (2023)

It doesn't make sense that private individuals are deciding the fate of infrastructure for everyone else. What about all the companies and all the countries that didn't get access? Unverified source (2026)

Moreover, frontier AI companies are seeking to develop AI with a specific skill that could very well unlock all others and turbocharge advances: AIs with the ability to advance research in AI. An AI system that would be as capable at AI research as t... more Unverified source (2024)