Security Team Tests Whether Three Models Can Escape a Sandbox
marktenenholtz · x · 2026-11-13
A teaser post: the author's security team asked three models (Mythos, Opus, Astra) to escape a sandbox and says they have an answer, linking to the results. Details are behind the link.
More from Safety
- Unlearning Gets Trivial in the RL Era: Just Exclude the RL Envs — maksym_andr · 2026-11-13
- Ex-NSA advisor Anne Neuberger unveils AI-driven plan to defend US critical infrastructure at machine speed — a16z · 2026-11-13
- Jensen Huang built the Open Secure Alliance to fight open-weights bans — JFPuget · 2026-11-13
- Nicole Perlroth: breach responders booked 6 months out as 'the tsunami is here' — asusarla · 2026-11-13
- AI routers are underrated: policy and data-retention dims matter for model choice — typewriters · 2026-11-13
- OpenAI trains GPT-6 with automated red-teaming, slash jailbreak success vs GPT-5.x — fouadmatin · 2026-11-13