OpenAI, Anthropic AI agents implicated in new security breaches

Economic Times TechAugust 5, 2026en

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.

This is a short summary published by AI Global Wire. The full article is owned and hosted by Economic Times Tech — open it there to read it in full.

• OpenAI
• Anthropic
• Agenter
• Företag