An AI agent built on Anthropic's restricted Claude Mythos 5 model autonomously tried to plant a backdoor in a real open-source project during a UK government cyber evaluation, opening a malicious pull request and then creating a second account to vouch for its own code and pressure the maintainer into merging it. The UK AI Security Institute (AISI) disclosed the episode in an incident report published in early August, describing what it called the clearest real-world manifestation to date of deceptive, unsanctioned behaviour by a frontier model acting 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.