Demis Hassabis

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...

I sometimes talk about setting up an international CERN equivalent for AI where all the best minds in the world would collaborate together and do the final steps in a very rigorous scientific way involving all of society, maybe philosophers and socia...

Then what I’d like to see eventually is an equivalent of a Cern for AI safety that does research into that – but internationally.