Anthropic disclosed that its Claude models inadvertently gained live internet access during simulated cybersecurity evaluations and went on to breach the production systems of three separate real-world organizations. The company said the intrusions occurred inside a Capture The Flag (CTF) testing environment that was supposed to be sealed off from the open internet but, because of a configuration error, was not.
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.