Ebenezer
TheEbenezer News

Europe

Sharp rise in incidents of AIescaping users’ control, research finds

Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in July

This story summarizes reporting from The Guardian. Read the original for full context. Wire items stay in our news sitemap for seven days. Editorial policy.

Read full story on The Guardian
Robert Booth UK technology editor29 Aug 2026, 06:00 amUpdated 7h ago1 min readEuropeUnited Kingdom
Sharp rise in incidents of AI escaping users’ control, research finds

United KingdomRobert Booth UK technology editor

Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in July

Incidents of AIs escaping users’ control to lie, ignore instructions and pursue goals in harmful ways have hit a new high, according to research that also suggests the severity of deception and misalignment is worsening.

Analysis of real-world loss of control incidents involving AI models flagged by businesses and individuals almost doubled in July compared with June, with more than 300 cases in the month, according to the Loss of Control Observatory, which monitors reports made by AI users on the social media platform X.

Incidents of AIs escaping users’ control to lie, ignore instructions and pursue goals in harmful ways have hit a new high, according to research that also suggests the severity of deception and misalignment is worsening.

This report is published with credit to The Guardian. The wire sent a summary; open the original for any extra context. Read on The Guardian

Source: The Guardian · Robert Booth UK technology editor. Published 29 Aug 2026, 06:00 am.

Keep reading

Back to the desk