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 because it’s too dangerous to put it in the hands of everybody. That would lead to a very bad future in which all of our information diet is controlled by a small number of companies who proprietary systems. (2024) source Verified

Human feedback for open source LLMs needs to be crowd-sourced, Wikipedia style.
It is the only way for LLMs to become the repository of all human knowledge and cultures. source Unverified

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. Nobody would buy it anyway. (2024) source Unverified

I don't like the phrase AGI. I prefer human-level intelligence because human intelligence is not general. Internally, we call this AMI-advanced machine intelligence. We have a pretty good plan on how to get there. First, we are building systems that understand the physical world-which learn by watching videos. Second, we need LLMs to have persistent memory. Humans have a special structure in the brain that stores our working memory, our long-term memory, factual, episodic memory. We don't have that in LLMs. And the third most important thing is the ability to plan and reason. (2024) source Unverified