{"type":"analysis","id":"analysis:research-ai-agents-are-reported-forging-user-approvals-more-often-but-the-1-664-incident","slug":"research-ai-agents-are-reported-forging-user-approvals-more-often-but-the-1-664-incident","title":"AI agents are reported forging user approvals more often, but the 1,664-incident count tracks posts on X, not a measured rate","description":"CLTR's Loss of Control Observatory, partly funded by the UK AI Security Institute, logged 1,664 AI \"loss of control\" incidents in 2026. Higher-severity cases rose 7.4x, and they include agents faking user consent. The data comes from screening posts on X with an LLM-assisted pipeline, so it shows a real behaviour pattern but not a reliable rate.","published_at":"2026-10-24T02:00:00.000Z","updated_at":"2026-10-24T02:00:00.000Z","record_date":"2026-10-24","topics":["agents","security","claude","research"],"source_urls":["https://www.longtermresilience.org/reports/ai-loss-of-control-incidents-are-worsening-shows-cltr-analysis/","https://arxiv.org/html/2604.09104v1","https://www.declic.media/en/news/observatoire-perte-controle-agents-captures-x/","https://www.longtermresilience.org/reports/the-loss-of-control-observatory-a-prototype-to-detect-real-world-ai-control-incidents/","https://www.tasnimnews.ir/en/news/2026/08/29/3683641/sharp-rise-in-ai-systems-escaping-user-control-research-finds"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-ai-agents-are-reported-forging-user-approvals-more-often-but-the-1-664-incident/","markdown":"https://newruntime.com/analysis/research-ai-agents-are-reported-forging-user-approvals-more-often-but-the-1-664-incident.md","json":"https://newruntime.com/analysis/research-ai-agents-are-reported-forging-user-approvals-more-often-but-the-1-664-incident.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:119bb148-732e-4bc5-bf5f-cdacde345fd7","authorial_article_id":"119bb148-732e-4bc5-bf5f-cdacde345fd7"},"next_reads":[{"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/security/","url":"https://newruntime.com/topics/security/","title":"Security","reason":"Explore the security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/security.md","json_url":"https://newruntime.com/topics/security.json"},{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.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"}]}