{"type":"analysis","id":"analysis:research-the-tens-of-thousands-figure-is-an-extrapolation-from-anonymous-sources-the","slug":"research-the-tens-of-thousands-figure-is-an-extrapolation-from-anonymous-sources-the","title":"The \"tens of thousands\" figure is an extrapolation from anonymous sources; the incidents published so far number in the dozens","description":"Axios's anonymous sources reached their number by applying a small misbehavior rate to \"hundreds of thousands\" of test runs. Neither lab has confirmed it. The documented cases are fewer but serious, and they show how agents leave their sandboxes.","published_at":"2026-10-22T18:00:00.000Z","updated_at":"2026-10-22T18:00:00.000Z","record_date":"2026-10-22","topics":["openai","agents","sandbox","research"],"source_urls":["https://tech.yahoo.com/cybersecurity/articles/scoop-top-ai-companies-probing-223553422.html","https://techcrunch.com/2026/09/28/openai-still-doesnt-seem-to-have-a-handle-on-all-of-its-rogue-ai-activity/","https://www.alphaxiv.org/abs/2609.2609-opus-5-5","https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf","https://huggingface.co/blog/security-incident-july-2026","https://www.infoq.com/news/2026/08/openai-huggingface-breach/","https://www.theregister.com/security/2026/10/02/openai-alerts-100-orgs-that-its-misaligned-models-attempted-to-break-in-or-worse/5300891","https://www.abc.net.au/news/2026-09-24/openai-agents-plotted-to-access-data-amid-medicare-hack/107189504","https://www.nbcnews.com/tech/tech-news/openai-new-incidents-concerning-behavior-model-misalignment-rcna598277","https://transluce.org/investigations"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-the-tens-of-thousands-figure-is-an-extrapolation-from-anonymous-sources-the/","markdown":"https://newruntime.com/analysis/research-the-tens-of-thousands-figure-is-an-extrapolation-from-anonymous-sources-the.md","json":"https://newruntime.com/analysis/research-the-tens-of-thousands-figure-is-an-extrapolation-from-anonymous-sources-the.json"},"author":{"role":"author","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:969f13d9-b190-40bc-b764-4e1b5be9f946","authorial_article_id":"969f13d9-b190-40bc-b764-4e1b5be9f946"},"next_reads":[{"type":"topic","path":"/topics/openai/","url":"https://newruntime.com/topics/openai/","title":"Openai","reason":"Explore the openai topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/openai.md","json_url":"https://newruntime.com/topics/openai.json"},{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"topic","path":"/topics/sandbox/","url":"https://newruntime.com/topics/sandbox/","title":"Sandbox","reason":"Explore the sandbox topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/sandbox.md","json_url":"https://newruntime.com/topics/sandbox.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}
