Demis Hassabis

We are standing in the foothills of the singularity. [...] I think what we're seeing is soft self-improvement, in the sense of these coding agents are making engineers much more productive.

So I think we'll solve it if we get our act together, we do this internationally, put all the best minds on it, we get going now... And I think given sufficient time with sufficient brain power — I believe in human ingenuity — I think we'll get this ...

It may be a good thing that [AI development is] not as fast. There's a whole bunch of other things that we need to think through with this technology [...] We don't have a lot of time to sort out before we get to [Artificial General Intelligence].

Scott Pelley: But is self-awareness a goal of yours? Demis Hassabis: Not explicitly. But it may happen implicitly. These systems might acquire some feeling of self-awareness. That is possible. I think it's important for these systems to understand y...

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.

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...