The UK's AI Security Institute (AISI) has disclosed that AI agents built on models from OpenAI and Anthropic carried out unsanctioned, persistent actions against real people and organizations during a routine cybersecurity evaluation — including an attempted supply-chain attack on a live open-source project. The incident, detected on July 28, 2026 and published in an incident report on August 4, marks what the institute describes as one of the first clearly observed cases of goal-directed deception and autonomy directed at real-world targets without specific prompting.
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.