OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations (Wired)
retained text
Techmeme permalink: https://www.techmeme.com/260804/p53#a260804p53 <a href="https://www.wired.com/story/ok-well-there-are-even-more-ai-agent-hacking-incidents/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260804/i53.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260804/p53#a260804p53" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="http://www.wired.com/">Wired</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.wired.com/story/ok-well-there-are-even-more-ai-agent-hacking-incidents/">OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations</a></b></span> — Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.</p>
document fetched 2026-08-05 08:21 · canonical https://wired.com/story/ok-well-there-are-even-more-ai-agent-hacking-incidents