Ex-OpenAI safety researcher: Labs lack plans for rogue AI containment
RebeccaBellan · x · 2026-08-24
Citing incidents like the Hugging Face breach, Sam Adler, chief scientist at Guidelight and former OpenAI safety researcher, criticized frontier AI labs for a lack of transparency. He expressed surprise that these companies have not disclosed how they would handle a serious incident if a model were to escape their control.
Related event: Top AI Labs Lack Public Plans to Contain Rogue Models, Study Finds(3 posts)→
More from Safety
- New paper uses revealed-preference methods to unpack why AI agents cooperate — brwilder · 2026-10-16
- Anthropic gives METR employee-level access, waives right to block its risk assessments — TechCrunch AI · 2026-10-16
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Anthropic's GRAFT routes flagged gradients into a deletable adapter, cutting reward hacking to near zero — rohanpaul_ai · 2026-10-16
- Polymarket opens 50/50 market on more states banning Flock police cameras by end of 2026 — Polymarket · 2026-10-16
- Reproducing the Hugging Face security incident: a technical deep-dive, Part I — jessehu · 2026-10-16