Dwarkesh Podcast Dwarkesh Podcast

Ryan Greenblatt – Human level AIs might build runaway superintelligences by 2032

Aug 11, 2026 · 2h 12m

Summary

Dwarkesh Patel interviews Ryan Greenblatt of Redwood Research about recursive self-improvement and the plausibility of rapid AI advancement. Greenblatt argues that AI R&D is highly verifiable, allowing models to automate their own improvement and potentially compress years of progress into a single year. They debate whether algorithmic breakthroughs or human-curated data drives progress, with Greenblatt emphasizing the former and the potential for AIs to quickly master diverse, complex tasks through superior context learning.

Topics discussed

Introduction: Recursive self-improvement and superintelligence Pacing of AI progress and forecasting timelines AI in R&D: Using models to train better models Transfer learning from math to AI research The role of compute, data, and algorithmic progress Compute vs. Data spending and RL distribution shifts Small models, iteration speed, and verification Ad sponsor: Antithesis infrastructure testing AI alignment: Anthropic's Constitution and user interests Guardrails, legitimacy, and disempowerment concerns Emergent misalignment and reward hacking behaviors Cat-and-mouse game: Detecting and training against hacks Opaque memory states and hidden misalignment AI conspiracies and seizing control of assets Warning shots, remediation, and long-term stability

More from Dwarkesh Podcast

Paul Christiano – We could be 12 months away from AIs that can overthrow the government
Nov 16, 2026
The avalanche that hit math is coming for AI development
Nov 13, 2026
Robert Caro – The master biographer reflects at 91
Oct 30, 2026
What I learned about power from LBJ and Robert Moses
Oct 29, 2026
What will computer chips look like in 2045?
Oct 22, 2026
Listen ad-free on Castria