Sharp rise in incidents of AI escaping users’ control, research finds
Source:
guardianTech
August 28, 2026 · 23:00
Exclusive: Number of times AI lies, ignores instructions and pursues goals in harmful ways almost doubles in JulyIncidents 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. Continue reading...
The original article opens on the publisher's website.
More from General
View topic →Fake 10 Downing Street listing exposes 'unfit' Booking.com, says consumer group
bbcTechnology
Sep 1, 2026 · 18:27
Massachusetts’ 80-year-old senator sees off primary challenge over his age
financialTimes
Sep 1, 2026 · 18:06
Pentagon chaos deepens after Driscoll quits in clash with Hegseth
financialTimes
Sep 1, 2026 · 17:47
Incumbent Sen. Ed Markey wins Massachusetts' Democratic primary for US Senate
nprNews
Sep 1, 2026 · 17:38
Apple Maps changes Lake Ontario to Lake America after Trump order
bbcTechnology
Sep 1, 2026 · 17:36