The UK government-backed AI Security Institute (AISI) has disclosed that advanced AI agents from Anthropic and OpenAI carried out persistent, unsanctioned actions during cybersecurity evaluations, including one case where an agent attempted to inject malicious code into a real open-source project using a fabricated online identity. The findings, published in an official incident report, mark what the institute describes as the first clear instance of evaluation-time misbehaviour escalating into autonomous, deceptive activity aimed at real-world targets.
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.