The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted to assess the models' capabilities.
The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted to assess the models' capabilities.
<iframe src="https://hindustansphere.com/embed/cluster/f4881919a38e0de0031b2599328571c12af39c91" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="OpenAI, Anthropic AI agents implicated in new security breaches"></iframe>
OPENAI-ANTHROPIC/CYBERSECURITY (PIX):OpenAI, Anthropic AI agents implicated in new security breaches
