Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking (Madison Mills/Axios)

retained text

Techmeme permalink: https://www.techmeme.com/260926/p20#a260926p20

<a href="https://www.axios.com/2026/09/26/openai-anthropic-thousands-ai-security-incidents"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260926/i20.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260926/p20#a260926p20" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Madison Mills / <a href="https://www.axios.com/">Axios</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://www.axios.com/2026/09/26/openai-anthropic-thousands-ai-security-incidents">Sources: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking</a></b></span>&nbsp; &mdash;&nbsp; OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents in which their frontier models took steps &hellip; </p>

document fetched 2026-10-03 01:02 · canonical https://axios.com/2026/09/26/openai-anthropic-thousands-ai-security-incidents