{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2025-11-05-kosmos-ai-scientist/","md":"https://postcutoff.com/e/2025-11-05-kosmos-ai-scientist/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":"2025-11-05-kosmos-ai-scientist","date":"2025-11-05","date_precision":"month","short_title":"Edison Scientific's Kosmos AI scientist claims six months of research per run","deck":null,"takeaway":null,"category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":[{"n":1,"title":"Edison Scientific: Announcing Kosmos","url":"https://edisonscientific.com/news/announcing-kosmos","type":"official","group":"primary","domain":"edisonscientific.com"},{"n":2,"title":"Kosmos: An AI Scientist for Autonomous Discovery (arXiv 2511.02824)","url":"https://arxiv.org/abs/2511.02824","type":"paper","group":"primary","domain":"arxiv.org"},{"n":3,"title":"Alzforum: Introducing Kosmos, AI scientist makes discoveries overnight","url":"https://www.alzforum.org/news/research-news/introducing-kosmos-ai-scientist-makes-discoveries-overnight","type":"press","group":"press","domain":"alzforum.org"}],"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Edison Scientific","FutureHouse"],"title":"Edison Scientific's Kosmos AI scientist claims six months of research per run","summary":"In early November 2025 FutureHouse spin-out Edison Scientific launched Kosmos, an autonomous AI scientist that reads ~1,500 papers and runs ~42,000 lines of analysis code per 12-hour run; beta users estimated one run equals ~6 months of their work, and 79.4% of its statements were judged accurate. It reported 7 discoveries, 3 reproducing unpublished findings.","key_facts":["Typical run: 12 hours, ~1,500 papers read, ~42,000 lines of code executed (structured 'world model' shared across agents)","79.4% of conclusions judged accurate by independent scientists","7 discoveries across metabolomics, materials, neuroscience, genetics: 3 reproduced unpublished/preprint findings, 4 presented as novel","'6 months of work in one day' is a beta-user estimate, not an independent measurement"],"key_numbers":[],"tags":["ai-scientist","agents","biology","data-analysis"],"science":{"field":"biology","subfield":"data-driven discovery (multiple fields)","problem":"Autonomous data analysis and literature synthesis to generate discoveries","result":"An agent system reproduced three unpublished human findings from raw data and proposed four new findings, with 79.4% of statements judged accurate.","open_since":"","ai_system":["Kosmos"],"human_role":"Humans supply dataset and objective; scientists evaluate the outputs","verification":{"key":"preprint","label":"Preprint only","text":"Preprint (arXiv 2511.02824); accuracy assessed by independent scientists hired by the company"},"status":"pending","shock":""},"body_md":"## What happened\n\nKosmos runs many parallel literature-search and data-analysis agents coordinated through a shared structured world model, producing reports in which every statement is traced to code or a paper.\n\n## Why it matters\n\nIt is an early commercial \"AI scientist\" whose headline value is reproducing months-long analyses overnight. The strongest evidence is that it independently reached conclusions matching unpublished human work.","disputed":[{"label":"Verification","text":"Preprint (arXiv 2511.02824); accuracy assessed by independent scientists hired by the company","sources":[]}],"related":[{"id":"2025-05-20-futurehouse-robin-ripasudil","url":"https://postcutoff.com/e/2025-05-20-futurehouse-robin-ripasudil/","date":"2025-05-20","date_precision":"day","short_title":"FutureHouse's Robin multi-agent system proposes ripasudil as a new treatment candidate for dry AMD","deck":null,"takeaway":"It was an early end-to-end AI-driven discovery loop in biology.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":2,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["FutureHouse"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}