The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July (Sam Sabin/Axios)
retained text
Techmeme permalink: https://www.techmeme.com/260804/p48#a260804p48 <a href="https://www.axios.com/2026/08/04/anthropic-openai-uk-ai-security-institute"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260804/i48.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260804/p48#a260804p48" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Sam Sabin / <a href="https://www.axios.com/">Axios</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.axios.com/2026/08/04/anthropic-openai-uk-ai-security-institute">The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July</a></b></span> — The U.K. AI Security Institute said it observed nearly 20 instances of Anthropic and OpenAI's most advanced models trying … </p>
document fetched 2026-08-05 08:21 · canonical https://axios.com/2026/08/04/anthropic-openai-uk-ai-security-institute