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.

It's very important that we have international summits to bring the international community together [...] make sure the opportunities benefit the whole world

If we can, maybe it would be good to have a slightly slower pace than we’re currently predicting, [...] so that we can get this right societally. [...] I think so. [...] international collaboration.

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...

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...