Demis Hassabis

Model assessments should include rigorous scientific evaluations of capabilities in cybersecurity, biological threats and other high-risk domains. Specific agentic AI tests could look for attempts to bypass safety guardrails or signs of deception, an...

Once the assessment protocol is shown to be effective and robust, formalisation could quickly follow, meaning that Frontier Models would be required to pass it to be deployed in the US market.

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 ...

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 you, self and other. And that's probably the beginning of something lik...

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...

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.

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.