Demis Hassabis

endowing rogue nations or terrorists with tools to synthesize a deadly virus. [...] keep the “weights” of the most powerful models out of the public’s hands. (2025) source Unverified

Yeah, I think those systems would be right on the boundary. So I think most emergent systems, cellular automata, things like that could be model-able by a classical system. You just sort of do a forward simulation of it and it’d probably be efficient enough. Of course there’s the question of things like chaotic systems where the initial conditions really matter and then you get to some uncorrelated end state. Now those could be difficult to model. So I think these are kind of the open questions, but I think when you step back and look at what we’ve done with the systems and the problems that we’ve solved, and then you look at things like Veo 3 on video generation sort of rendering physics and lighting and things like that, really core fundamental things in physics, it’s pretty interesting. I think it’s telling us something quite fundamental about how the universe is structured in my opinion. So in a way that’s what I want to build AGI for is to help us as scientists answer these questions like P equals NP. source Unverified