Yann LeCun

Current LLMs are intrinsically unsafe, but with world models, guardrail objectives can be implemented — so by construction, they will not knowingly produce actions that will produce dangerous results.

Making technology developers liable for bad uses of products built from their technology will simply stop technology development,

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...

Well, my first reaction to this is that calling for a delay in research and development smacks me of a new wave of obscurantism, essentially, like why slow down the progress of knowledge and science? Then there is the question of products, like, you ...

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.