{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-07-09-anthropic-claude-plays-robotics/","md":"https://postcutoff.com/e/2026-07-09-anthropic-claude-plays-robotics/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":"2026-07-09-anthropic-claude-plays-robotics","date":"2026-07-09","date_precision":"day","short_title":"Anthropic: LLMs fail at direct robot joint control but succeed supervising controllers","deck":"From Anthropic's 'Claude plays robotics' study.","takeaway":"On July 9, 2026 Anthropic published \"Claude plays robotics\", which tested twelve models from five providers on simulated and physical robots.","category":"robotics","category_label":"Robotics","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Anthropic: Claude plays robotics","url":"https://www.anthropic.com/research/claude-plays-robotics","type":"official","group":"primary","domain":"anthropic.com"}],"official":1,"filed":"2026-10-01","updated":"2026-10-01","orgs":["Anthropic"],"title":"Anthropic's 'Claude plays robotics': LLMs fail at direct joint control but succeed when supervising controllers","summary":"On July 9, 2026 Anthropic published \"Claude plays robotics\", which tested twelve models from five providers on simulated and physical robots. Models mostly fail when they must drive joints directly, with 0–5.5% direct manipulation success (best: Claude Mythos Preview). They complete real navigation and manipulation tasks when they supervise a pretrained controller or a VLA policy, or use simple tools such as a compass.","key_facts":["Authors: Shmuel Berman, Michael Ilie, Jia Deng, Daniel Freeman","12 models from 5 providers, several Claude generations","Direct manipulation success 0–5.5%; Claude Mythos Preview highest at 5.5%","Quadruped: newer models reach 'limited but meaningful' whole-body control (balancing almost two seconds); no model stood a collapsed humanoid up","VLA supervision on LIBERO-40 raised success substantially for all models","A compass tool beat visual self-views; extended reasoning helped little and sometimes hurt"],"key_numbers":[],"tags":["robotics","evals","embodiment","vla","manipulation","locomotion"],"science":null,"body_md":"## What happened\n\nA systematic eval of general LLMs as robot controllers at several levels of abstraction, from raw joint commands up to\nsupervising pretrained policies.\n\n## Why it matters\n\nThe study measures how far general frontier models are from embodied control. The answer depends heavily on the interface: high-level\nsupervision already works, while low-level control improves only now and then from one generation to the next.","disputed":[],"related":[{"id":"2026-07-24-anthropic-andon-project-pilot-drone-bench","url":"https://postcutoff.com/e/2026-07-24-anthropic-andon-project-pilot-drone-bench/","date":"2026-07-24","date_precision":"day","short_title":"Project Pilot: Anthropic and Andon Labs test whether AI models can fly a surveillance drone (Drone-Bench)","deck":null,"takeaway":"Autonomous aerial surveillance is a clearly dual-use capability, and the study suggests frontier models were close to it by mid-2026, except for 3D mapping.","category":"benchmark","category_label":"Benchmarks","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":3,"filed":"2026-10-01","updated":"2026-10-01","orgs":["Anthropic","Andon Labs"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-01","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-01","run":null,"sources_read":null,"updated":"2026-10-01","human_review":null,"version":{"date":"2026-10-07"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":39,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":9,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":100,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":39,"in_training_data":false}],"short_url":null}