Geoffrey Hinton

Let's open source nuclear weapons too to make them safer. The good guys (us) will always have bigger ones than the bad guys (them) so it should all be OK. Verified source (2023)

Oh, it certainly could, yes. I think anybody who said that there's no way it'll lead to the extinction of humans just isn't facing reality. AI Verified source (2026)

We should be careful to construct in a way where we still continue to exist, and we can live in harmony with it. [...] Very few resources are being put into it. Maybe one percent. AI Verified source (2026)

I think the people who run the big tech companies — the very high up people, not all of them, but a lot of them — think we are going to get to AGI. Whoever gets there first is going to have immense power and be able to make immense profits by replaci... more AI Verified source (2026)

We somehow have to have a way of — when AI agents replace people — doing what Bill Gates has suggested recently. We have to have a way of taxing the AI agents, so there's still a tax base. AI Verified source (2026)

When you open source a big model and give people the weights [...] You get people using that open source model and training it, refining it to do something bad like cyberattacks or making biological weapons because it's much easier to refine the mode... more AI Verified source (2025)

I don’t think they should scale this up more until they have understood whether they can control it. We’ve entered completely unknown territory. We’re capable of building machines that are stronger than ourselves, but what if we develop machines that... more AI Verified source (2023)

If you ever went out with a car that had no brake, boy, you are in trouble if you go down a hill. But you're in even more trouble if there's no steering wheel. AI Verified source (2026)

If you ever went out with a car that had no brake, boy, you are in trouble if you go down a hill. But you're in even more trouble if there's no steering wheel. [...] They want a very fast car with no steering wheel. AI Verified source (2026)

Philanthropy is very important for AI safety right now. [...] The problem is philanthropists are funding most of it; ninety-nine per cent of corporate investment goes to making AI models smarter and one per cent goes to safety. AI Verified source (2026)

Scott Pelley: You believe these systems have experiences of their own and can make decisions based on those experiences? Geoffrey Hinton: In the same sense as people do, yes. Scott Pelley: Are they conscious? Geoffrey Hinton: I think they probably d... more Unverified source (2024)

If you ever went out with a car that had no brake, boy, you are in trouble if you go down a hill. But you're in even more trouble if there's no steering wheel. [...] [Those opposed to regulation say] unregulated AI is like the accelerator, and regula... more AI Verified source (2026)

GH: I’m an expert on trying to get the technology to work, not an expert on social policy. One place where I do have technical expertise that’s relevant is [whether] regulators should insist that you can explain how your AI system works. I think that... more AI Verified source (2017)

We don't know whether we can co-exist with super intelligent AI. AI Unverifiable source (2026)