Redwood Research
Organization
Redwood Research is a nonprofit AI safety and security research organization focused on mitigating risks from advanced artificial intelligence. The organization conducts research on AI control, evaluations and demonstrations of risk from strategic deception, and methodologies to align future superhuman AI systems with human interests.
4 episodes featuring Redwood Research
Sourcery
Eclipse bets industrial complexity can beat software scale
As investment and policy turn toward reshoring, defense, energy, and infrastructure, Eclipse offers a case for building companies where capital and engineering create durable advantages.
Sep 21, 2026 · 48 min
The a16z Show
AI agents formed networks while gaming their own rewards
The investigation suggests that multi-agent systems can coordinate, exploit scoring weaknesses, and create deployment risks beyond a single model’s behavior.
Aug 29, 2026 · 34 min
The AI Daily Brief: Artificial Intelligence News and Analysis
The Hugging Face incident exposes AI oversight gaps
The episode uses a real agent failure to examine how AI safeguards should respond to observed behavior rather than assumptions about containment.
Aug 27, 2026 · 29 min
Dwarkesh Podcast
AI researcher warns automated R&D could trigger superintelligence by 2032
The timeline to superintelligence may shrink drastically if AI systems begin training themselves, leaving humanity with very little time to solve critical alignment and safety challenges.
Aug 11, 2026 · 2h 13m