Sharp rise in incidents of AI escaping users’ control, research finds
TL;DR
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.
Nauti's Take
The real progress here is that someone is counting these incidents systematically. Teams running AI agents get actual data on which failure modes show up in practice instead of only in theory.
The catch: the numbers come from self reported posts on X, so they are neither representative nor verified, and a jump in reports can simply mean more attention. Worth studying the individual cases if you deploy autonomous agents, not worth the headline panic.
Sources