Why the AI Race Undermines Safety (with Steven Adler)
Former OpenAI safety researcher Stephen Adler discusses governing increasingly capable AI, including competitive race dynamics, gaps in testing and alignment, chatbot mental-health impacts, economic effects on labor, and international rules and audits before training superintelligent models.
Stephen Adler is a former safety researcher at OpenAI. He joins the podcast to discuss how to govern increasingly capable AI systems. The conversation covers competitive races between AI companies, limits of current testing and alignment, mental health harms from chatbots, economic shifts from AI labor, and what international rules and audits might be needed before training superintelligent models.
Researcher Oly Sourbut discusses how AI tools might strengthen human reasoning, from fact-checking and scenario planning to honest AI standards and better coordination, and explores how to keep humans central while building trustworthy, society-wide sensemaking.
Technical specialist Nora Ammann of the UK's ARIA discusses how to steer a slow AI takeoff toward resilient, cooperative futures, covering risks from rogue AI and competition to scalable oversight, formal guarantees, secure infrastructure, and AI-supported bargaining.
David Duvenaud examines gradual disempowerment after AGI, exploring how economic and political power and property rights could erode, why AI alignment may become unpopular, and what forecasting and governance might require.
