John Schulman joins Dwarkesh podcast to debate RSI, RL, and AGI timelines
ZhongRuiqi · x · 2026-09-12
Dwarkesh releases a new episode featuring John Schulman, Cameron O'Neill, and Beren Millidge from Thinking Machines, discussing where human judgment still matters as models self-improve: teaching them to handle messy real-world tasks, applying taste to what works long-term, and specifying what we actually want.
Topics covered:
- Steelmanning the case against RSI
- What's driving Chinese labs' progress
- How automated AI researchers will be trained
- Whether long-horizon RL elicits AGI
- The sim-to-real gap and how much progress data explains
- Why RL works so well, Move 37 and entropy collapse
- Rapid-fire AGI timelines
More from AGI Musings
- What if millions of AIs' combined incentives create irreversible outcomes? — PierceLilholt · 2026-10-28
- Coding matters less than problem-finding: the shift from code engineers to product engineers — CtrlAltDwayne · 2026-10-28
- Rachel Thomas points to classic paper on articulating the value of not building tech — math_rachel · 2026-10-28
- Hypothetical $2T Anthropic IPO framed as channeling $100B+ a year into the real economy — sanjaykalra · 2026-10-28
- Biotech CEO: drug discovery will lag in the AI revolution, not lead it — vaibhavbetter · 2026-10-28
- AI cyber-wreckage noise far outstrips actual damage so far, argues new analysis — timigod · 2026-10-28