{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-11-10-gemini-robotics-2-5-asimov-jailbreak/","md":"https://postcutoff.com/e/2026-11-10-gemini-robotics-2-5-asimov-jailbreak/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-11-10-gemini-robotics-2-5-asimov-jailbreak","date":"2026-11-10","date_precision":"day","short_title":"Google DeepMind releases Gemini Robotics 2.5 to partners and open-sources the ASIMOV-Jailbreak robot-safety benchmark","deck":null,"takeaway":null,"category":"robotics","category_label":"Robotics","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Google DeepMind: Gemini Robotics 2.5 accelerates real-world general dexterity","url":"https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/","type":"official","group":"primary","domain":"deepmind.google"},{"n":2,"title":"Google DeepMind on X (475k views)","url":"https://x.com/GoogleDeepMind/status/2120169787896525104","type":"official","group":"primary","domain":"x.com"},{"n":3,"title":"Ars Technica: DeepMind reveals Gemini Robotics 2.5 and open safety benchmark ASIMOV-jailbreak","url":"https://arstechnica.com/google/2026/11/deepmind-reveals-gemini-robotics-2-5-and-open-safety-benchmark-asimov-jailbreak/","type":"press","group":"press","domain":"arstechnica.com"}],"official":2,"filed":"2026-11-12","updated":"2026-11-12","orgs":["Google DeepMind","Apptronik","Mercedes-Benz"],"title":"Google DeepMind releases Gemini Robotics 2.5 to partners and open-sources the ASIMOV-Jailbreak robot-safety benchmark","summary":"On Nov 10, 2026 Google DeepMind released Gemini Robotics 2.5 to its robotics partners, reporting 30-100% higher success than earlier baselines on over 200 tasks and a 96% success rate for Apptronik Apollo 2 humanoids sorting brackets on Mercedes-Benz production lines in a proof of concept. It also open-sourced ASIMOV-Jailbreak, a benchmark of disguised unsafe requests to robots.","key_facts":["Evaluated on 200+ distinct tasks: 30-100% higher success than previous baselines depending on task type, tasks finished 20-30% faster (DeepMind)","Mercedes-Benz proof of concept: Apptronik Apollo 2 humanoids sorted automotive brackets into trays for assembly with 96% success","Skills shown: tool use (serving food with tongs), deformable objects such as laundry, delicate items; runs on Apollo 2 and the Franka Duo platform","Safety: inference-time reasoning guidance improved safe task completion by 33% around obstacles and 43% around nearby people; on ASIMOV-Jailbreak (hundreds of prompts disguising unsafe requests across dozens of scenes), Gemini 4 Argon resisted 99.5% vs 82% for Gemini Robotics-ER 2","Gemini 4 Argon generated simulated practice runs and digital twins used in development","Availability: robotics partners only; no public API mentioned","Apptronik CEO Jeff Cardenas: 'This is what we built Apollo for: useful work alongside people in real industrial settings'"],"key_numbers":[],"tags":["robotics","humanoids","vla","safety-benchmark","jailbreaks","manufacturing"],"science":null,"body_md":"## What happened\n\nDeepMind's robotics line moved from the Gemini Robotics 2 / ER 2 models to 2.5, with a factory proof of concept as the headline result.\nThe success figures are DeepMind's own.\n\n## Why it matters\n\nA frontier lab reporting humanoids at 96% on a real production-line task, together with an open benchmark for tricking robots into\nunsafe actions, marks the step from lab demos toward industrial pilots.","disputed":[],"related":[{"id":"2026-11-12-gemini-4-hydrogen","url":"https://postcutoff.com/e/2026-11-12-gemini-4-hydrogen/","date":"2026-11-12","date_precision":"day","short_title":"Google releases Gemini 4 Hydrogen, a fast Gemini 4 model that edges past Argon, and brings it to Search for everyone","deck":null,"takeaway":"A month after Argon launched as Google's flagship, a cheaper and faster model scores slightly above it on the main independent index.","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":14,"official":5,"filed":"2026-11-12","updated":"2026-11-13","orgs":["Google DeepMind","Google"]}],"people":[],"posts":[{"id":"x-googledeepmind-2120169787896525104","title":"“Gemini Robotics 2.5 is here. 🤖 Our latest physical AI is able to learn hundreds of…”","url":"https://postcutoff.com/p/x-googledeepmind-2120169787896525104/"}],"videos":[],"models":[],"changes":[{"date":"2026-11-12","type":"filed","text":"Created (news agent)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-12","run":null,"sources_read":null,"updated":"2026-11-12","human_review":null,"version":{"date":"2026-11-12"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":194,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":133,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":224,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":163,"in_training_data":false}],"short_url":null}