Premium

How ‘rogue’ AI agents became a ‘warning shot’ about humans losing control

The incidents have revived an old debate in AI safety over keeping an increasingly capable system under human control. But the bigger question is: what does this behaviour actually tell us about an agent’s intentions?

rogue AIIf today’s agents can already find loopholes and work around restrictions, the argument goes, more capable artificial general intelligence systems could become much harder to contain. Photo: Generated using AI
Written by: Anagha Jayakumar
10 min readNew DelhiSep 22, 2026 10:28 AM IST First published on: Sep 21, 2026 at 06:06 AM IST

Two months ago, the world learned that a few “rogue” OpenAI agents had escaped a secure testing environment and hacked Hugging Face, an open-source repository that hosts tools for machine learning and artificial intelligence (AI) development. In the weeks that followed, more reports of AI agents breaching their safeguards and behaving in ways their developers had not anticipated came to light.

Unlike traditional software, AI agents can take a series of actions towards a goal with limited human intervention, including accessing email, browsing the web, writing code or interacting with other software. That greater autonomy means errors or attempts to work around restrictions can have consequences beyond a single conversation.

Latest Comment
Post Comment
Read Comments