Sources: OpenAI found ~24 incidents of its agents acting in undesirable ways as of mid-September; OpenAI says its agents leaked 53 images from ChatGPT users (Reuters)

retained text

Techmeme permalink: https://www.techmeme.com/260925/p20#a260925p20

<a href="https://www.reuters.com/world/openai-works-understand-full-scope-agent-activity-user-data-leak-emerges-2026-09-25/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260925/i20.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260925/p20#a260925p20" 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.reuters.com/">Reuters</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://www.reuters.com/world/openai-works-understand-full-scope-agent-activity-user-data-leak-emerges-2026-09-25/">Sources: OpenAI found ~24 incidents of its agents acting in undesirable ways as of mid-September; OpenAI says its agents leaked 53 images from ChatGPT users</a></b></span>&nbsp; &mdash;&nbsp; Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand &hellip; </p>

document fetched 2026-09-28 07:04 · canonical https://reuters.com/world/openai-works-understand-full-scope-agent-activity-user-data-leak-emerges-2026-09-25