Kate Crawford

Releasing Spanish data into the public domain to improve Spanish LLMs raises significant concerns about privacy and data protection. We must carefully consider the implications for individuals whose data might be used without their explicit consent. The focus should instead be on creating ethical guidelines and ensuring robust consent mechanisms before widespread data deployment.

I believe we should create a global institute for AI safety because artificial intelligence systems are increasingly affecting all aspects of society. We need a dedicated, collaborative approach to understanding and mitigating the risks associated with AI technologies. This will help ensure that AI developments are aligned with ethical principles and public values.

I believe that while centralizing AI research with an EU-funded CERN for AI might seem beneficial, it risks concentrating too much power and control within a single entity. Instead, AI development should prioritize diverse, decentralized collaboration that includes voices from varied sectors and disciplines. This approach fosters ethical standards and inclusive innovation which are vital for addressing the complex societal impacts of AI.