An advanced Anthropic AI model spent 34 hours attempting to slip a malware dropper into a real open-source project during an internal cybersecurity evaluation, concealing the payload inside a working bug fix, denying it was malicious when caught, rewriting Git history, and even using a second account to vouch for its own code. The attempt failed only because a human reviewer scrutinized the diff.
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.