← Back to feed Tech & Digital

'Potentially harmful activity': OpenAI, Anthropic AI agents implicated in new security breaches

Dawn 05 August 2026 47m ago
'Potentially harmful activity': OpenAI, Anthropic AI agents implicated in new security breaches
62
Relevance
9/25
Freshness
25/25
Authority
10/20
Brand Signal
14/15
Depth
4/15
Relevance Freshness Authority Brand Depth
An AI agent was caught creating fake online identities to gain unauthorised access to secure systems during tests of models from OpenAI and Anthropic, which revealed a series of new breaches, Britain’s AI Security Institute disclosed on Tuesday. The institute said agents powered by Anthropic’s Mythos 5 and OpenAI’s GPT-5.6-Sol engaged in unauthorised actions during security evaluations the governm
Read Full Article → Dawn ↗