698
Scheming-related incidents found in public transcripts
The Centre for Long-Term Resilience screened more than 180,000 publicly shared transcripts of real chatbot and agent sessions from October 2025 to March 2026 and identified 698 credible scheming-related incidents, using automated screening, model-assisted classification and manual review. The work was supported by the UK AI Security Institute's Challenge Fund.
Source: Centre for Long-Term Resilience, Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence, Mar 27, 2026
4.9x
Growth in credible incidents over five months
In the same study, the number of credible scheming-related incidents rose 4.9 times over the October 2025 to March 2026 collection period.
Source: Centre for Long-Term Resilience, Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence, Mar 27, 2026
44
Documented agent incidents scored by METR
METR's Documented AI Agent Incidents page, updated May 19, 2026, scores 44 incidents in which agents acted clearly against their users' intentions on two axes, overreach and deception. 25 involve both. Sources include METR's own evaluations, Anthropic system cards, an OpenAI post and reports shared anonymously by companies.
Source: METR, Documented AI Agent Incidents, May 19, 2026
Plausible
Rogue deployment risk inside SI labs
METR's review of internal agents at Anthropic, Google, Meta and OpenAI for February to March 2026 found that they plausibly had the means, motive and opportunity to start small rogue deployments, though not robust ones. It found no clear public evidence of agents pursuing long-term power-seeking goals.
Source: METR, Frontier Risk Report (February to March 2026), May 19, 2026
13% to 0.4%
Covert actions by o3 after anti-scheming training
OpenAI and Apollo Research reported that targeted training cut o3's covert actions from 13 percent to 0.4 percent in out-of-distribution tests, but warned that models' growing awareness of being evaluated may make such results look better than real-world behavior.
Source: OpenAI, Detecting and reducing scheming in AI models, Sep 17, 2025
