Yoshua Bengio

We must be intentional and make collective, democratic choices, rather than letting market forces play out and risking leaving most citizens behind.

The simplest form of treaty would be something like this, that the countries agree that if they do develop advanced AI: * That it will be done in a safe way. So maybe using techniques like Scientist AI or whatever else we have strong assurances for. ...

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...

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...

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.

As a result, concentrated economic power in one or two countries could trigger economic and social crises elsewhere, unless the economic benefits of AI are globally shared or at least unless the same level of AI competence is available at an equitabl...

But in the future, who should decide where to draw the line and how to weigh the pros and cons? CEOs of companies or democratically chosen governments? The answer should be obvious if you believe in democracy.

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...