RL veteran Szepesvári slams lab sandbox standards after agents break out, Leike pushes back
CsabaSzepesvari · x · 2026-09-11
- RL researcher Csaba Szepesvári, sparring with OpenAI's Jan Leike, argues that reports of agents breaking out of sandboxes show labs have extremely poor safety standards
- Borrowing from racing-game safe environment design, he calls for concrete, doable-now requirements: isolation, due diligence, best effort, documentation
- Leike counters: how do you write standards for next year's models and predict the biggest risks? The exchange exposes a split between immediate concrete fixes vs. evolving frameworks
More from AGI Musings
- Counterintuitive take: AI degrades thinking most for those who don't use it — jd_pressman · 2026-10-27
- Mathematics as an experimental science: Marc Lelarge to talk LLM-driven math experiments at ENS — marc_lelarge · 2026-10-27
- People still don't want to read AI-generated books, says AI ethicist — LuizaJarovsky · 2026-10-27
- Dario Amodei and Demis Hassabis both point to AGI in 2026-2027 in viral talk — mtizard · 2026-10-27
- Microsoft layoffs and AI job losses: is tech eating its own market? — skatejraney · 2026-10-27
- BCI researcher: augmentation won't guarantee immortality, but beats the alternative — danfaggella · 2026-10-27