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. (source)

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 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.

While transparency is important, requiring model cards before commercial release could stifle innovation and impose unnecessary burdens on developers. Instead, developers should focus on responsible usage and improvements over time.

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.

While interpretability in AI is important, imposing strict requirements on decision-making processes might hinder innovation. In many cases, the complexity that enables high performance can be inherently opaque. Rather than enforcing interpretability, we should focus on developing tools to better understand AI behavior without stifling progress.