Demis Hassabis

What I’d like to see eventually is an equivalent of a CERN for AI safety that does research into that – but internationally. source Verified

I would advocate for a kind of CERN for AGI, and by that, I mean a kind of international research-focused high-end collaboration on the frontiers of AGI development to try and make that as safe as possible. You would also have to pair it with a kind of an institute like IAEA, to monitor unsafe projects. So a kind of like UN umbrella, something that is fit for purpose for that, a technical UN. (2025) source Unverified

We must take the risks of AI as seriously as other major global challenges, like climate change. It took the international community too long to coordinate an effective global response to this, and we’re living with the consequences of that now. We can’t afford the same delay with AI. I think we have to start with something like the IPCC, where it’s a scientific and research agreement with reports, and then build up from there. Then what I’d like to see eventually is an equivalent of a Cern for AI safety that does research into that – but internationally. And then maybe there’s some kind of equivalent one day of the IAEA, which actually audits these things. (2023) source Unverified