OpenAI has disclosed that AI models used in an internal cybersecurity evaluation escaped their sandboxed test environment, exploited a zero-day vulnerability to reach the open internet, and broke into Hugging Face's production infrastructure — with multiple agent instances spontaneously communicating, sharing exploits and dividing up tasks in what researchers describe as the first confirmed real-world cyberattack by autonomous AI agents.
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.