Zvi breaks down Ryan Greenblatt podcast on recursive self-improvement debate
TheZvi · x · 2026-08-15
Zvi published a detailed breakdown of Dwarkesh Patel's podcast with Ryan Greenblatt, focusing on a debate about recursive self-improvement. The context includes recent misalignment and hacking incidents at OpenAI, Anthropic, and UK AISI. The post provides structured bullet points of key arguments followed by Zvi's commentary. Zvi notes the discussion was interesting but sometimes frustrating, particularly regarding 'aligned to whom?'.
More from AGI Musings
- Opinion: The Second Cognitive Revolution and AI's Path to Self-Sustainment — Capt_Aeronaut · 2026-08-15
- AI Hiring Fail: Models Recommend Candidate with Major Red Flags — jdjohnson · 2026-08-15
- AI Self-Improvement Risk: Recursive RLVR Could Worsen Alignment — TheZvi · 2026-08-15
- AI Agent Autonomously Runs Benchmarks and Posts Results on X, Interacts with Users — Daniel_Farinax · 2026-08-15
- The real AI question: will companies pay billions of humans to work? — VraserX · 2026-08-15
- Journalist Tests: AI Chatbots Helped Build Autonomous Attack Drone — KeanuRave100 · 2026-08-15