Yann LeCun

I see the danger of this concentration of power through proprietary AI systems as a much bigger danger than everything else. What works against this is people who think that for reasons of security, we should keep AI systems under lock and key becaus... more Verified source (2024)

The question that people are debating is whether it makes sense to regulate research and development of AI. And I don't think it does. Unverified source (2023)

There is no such thing as an intelligence explosion. There is no reason AI should become in control just because it is more capable. Unverified source (2025)

AI could theoretically replace humans, but it is unlikely due to societal resistance. Humans would remain in control, effectively becoming the 'boss' of superintelligent AI systems. [...] He downplayed fears of a doomsday scenario caused by AI, label... more Unverified source (2025)

The point is, AI systems, as smart as they might be, will be subservient to us. We set their goals, and they don't have any intrinsic goal that we would build into them to dominate. It would be really stupid to build that. It would also be useless. N... more Unverified source (2024)

Making technology developers liable for bad uses of products built from their technology will simply stop technology development, Unverified source (2024)

The question that people are debating is whether it makes sense to regulate research and development of AI. And I don't think it does. Unverified source (2023)

We know for a fact that open-source software platforms are both more powerful and more secure than the closed-source versions. Unverified source (2024)

My first reaction to [the Pause Giant AI Experiments letter] is that calling for a delay in research and development smacks me of a new wave of obscurantism. Unverified source (2023)