Yann LeCun

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)

I believe that banning open-source AI models is not the solution. The potential for misuse exists in many technologies, but the benefits of open research and collaboration far outweigh the risks. We should focus on robust safeguards and ethical guidelines instead.

I believe people should have the right to know if they are speaking to an AI. Transparency is crucial in fostering trust and ethical interactions between humans and artificial intelligence systems.

I believe AI has the potential to democratize access to information and technology, rather than concentrate power. If we prioritize open research and collaboration, AI can empower individuals and smaller organizations, providing tools that were once only available to large corporations or governments.

I believe that creating a global institute for AI safety may not be the most effective approach. Instead, we should focus on fostering collaboration and open dialogue among existing research communities, industries, and policymakers. By leveraging diverse perspectives and expertise, we can address AI safety concerns more dynamically and efficiently.

I believe we should consider repealing the EU AI Act. While regulation is important, the current framework could stifle innovation and make it difficult for startups and researchers to develop groundbreaking AI technologies. We need a balanced approach that encourages progress while addressing ethical concerns.

I believe that establishing international AI ethics boards could stifle innovation and slow down the progress of AI technology. Instead, we should encourage collaboration and open discussions among researchers, developers, and policymakers to create flexible guidelines that can adapt to the rapid pace of technological change.