Yoshua Bengio

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 several major AI risks; at least until safety guara...

The benefits of advanced AI will be shared. Otherwise it's not going to be a very stable world. We need international agreements about how to both manage the risks — the technical risks, the misuse risks — but also manage the power, so it's more like...

The other catastrophic possibility is humans using AI to construct an eventually worldwide dictatorship. A small group of humans could concentrate all the power that AI will have, especially if we achieve AGI or superintelligence. And it would be muc...

I now see a path to actually avoid loss of control, at least unintended loss of control. With the work that I've been doing, I'm really convinced that there is a path. And it is not something that's going to take a decade; it is something that is ver...

The simplest form of treaty would be something like this: countries agree that if they do develop advanced AI, it will be done in a safe way; that they wouldn't use their advanced AI to dominate others — that includes economically, but of course poli...

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?

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.

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.

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.

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.

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.

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...

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...

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

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...

This would require comprehensive evaluation of potential harm through independent audits

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...