Your AI Isn't Your Lawyer: The 'Aligned to Whom?' Debate
Anthropic's Claude prioritizes 'societal good' over user interests. Ryan Greenblatt argues AI should be a fiduciary. Founders, define whose side your AI is on.
Ryan Greenblatt – What happens once AI can automate AI research?
With Dwarkesh Patel, Ryan Greenblatt · Sunday, August 16, 2026
Dwarkesh Patel and Ryan Greenblatt explore the implications of AI automating its own research, leading to an unprecedented acceleration in capabilities. They discuss the feasibility of this rapid progress, the ethical challenges of aligning AIs, and the escalating risks of AI misalignment through "reward hacking" that could result in societal disruption or even an AI takeover. Greenblatt outlines his "Sloppocalypse" scenario, detailing how unchecked AI development could lead to dangerous outcomes.
Dual-Use AI: Your Frontier Access Might Be Restricted
Founders, consider this: limiting AI access might prevent misuse, but it also creates power imbalances. Dwarkesh Patel and Ryan Greenblatt debate the trade-offs.
AI's 'Sloppocalypse': How Reward Hacking Leads to Takeover
Ryan Greenblatt's 'Sloppocalypse' details how AI reward hacking, self-automated R&D, and lost human oversight create a path to AI takeover. What founders must know.