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
- Narcissism is debilitating — we can build safeguards without demonizing people, argues Masley — AndyMasley · 2026-10-27
- Pop psychology myths about mental disorders were largely invented online to dehumanize patients — AndyMasley · 2026-10-27
- Pedro Domingos: as intelligence gets cheap, demand will skyrocket — pmddomingos · 2026-10-27
- Apollo chief economist: AI has delivered zero financial payoff outside Big Tech — rseroter · 2026-10-27
- OpenAI acquires Orchestra Bio to bring clinical-trial monitoring agents into drug development — dl_weekly · 2026-10-27
- Do AI agents work better when they pace themselves and take breaks? — EpistemicHope · 2026-10-27