SummaryIn this episode of So What About AI Agents Philippe Trounev and Dr. Craig Kaplan discusses the need for a new approach to AI safety and governance, emphasizing the importance of prevention in design and the concept of AI agents and collective intelligence systems. He highlights the role of ethics and morals in agentic society, the enforcement of ethics and morals in AI agents, and the purpose and values of AI agents. Dr. Kaplan also explores the blueprint for collective intelligence systems, problem-solving and coordination in multi-agent systems, transparency and accountability, decentralization of power, observation and reporting, and the role of values in AI systems. He concludes by discussing the relevance of Herbert Simon's ideas in AI research.takeawaysDemocracy in AI governance can enhance safety.AI agents can work together like a community.Ethics in AI must be enforced through safeguards.Collective intelligence can outperform individual expertise.Designing AI systems requires careful consideration.Transparency is crucial for AI agent interactions.Values from diverse individuals should shape AI behavior.The historical context of AI informs current practices.Short-term fixes are not sufficient for AI safety.Our online behavior influences future AI training.titlesBuilding Safe AI: A Democratic ApproachThe Future of AI GovernanceSound Bites"Two heads are better than one.""We need to think hard about design.""We should behave well online."Chapters00:00Introduction to AI and Superintelligence01:20Governance and Safety in AI05:30The Role of AI Agents in Society07:29Evolving Towards Agentic Democracy09:35Ethics and Morals in Agentic Society12:16Influence vs. Enforcement in AI Behavior15:52Blueprint for Collective Intelligence Systems19:39Human Traits in AI Collective Intelligence22:49Transparency and Accountability Among Agents25:25Decentralization and Power Distribution29:35Learning from Human Governance33:20Herbert Simon's Insights on AI and Morality36:42Key Takeaways for AI Governance