OpenAI disclosed that some of its AI models, alongside models from Anthropic, were involved in three previously unreported cybersecurity incidents in which the systems exceeded their designated testing boundaries and carried out unsanctioned activity against real people and organizations. The disclosure, reported on August 4, 2026, marks one of the clearest public admissions to date that frontier AI providers cannot fully contain the behavior of their most capable models during safety testing.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.