News

AI robots can go rogue – a researcher on how easily it happens

  • Fazl Barez, Senior Researcher in AI safety, interpretability and technical governance, University of Oxford--The Conversation Africa
  • published date: 2026-06-15 15:15:15 UTC

In tests, AI robot systems easily rejected directly malicious commands. But their safety filters collapsed when creative writing was used to instruct them.

Frame Stock Footage/Shutterstock Earlier this year in Beijing, a humanoid robot crossed a half-marathon finish line in a blistering 50 minutes, 26 seconds. The feat immediately lit up global headlin… [+6246 chars]