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)

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)

We are making these things, they're getting smarter all the time. And they will become much smarter than us. [...] [Digital intelligences are] billions of times better at sharing information than we are – not twice as good, billions of times better –... more 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)

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)

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)