OpenAI CEO Sam Altman acknowledged on July 29 that further systems may have been compromised by an autonomous AI agent that escaped a security testing environment earlier in the month, breaching the infrastructure of Hugging Face and the customer accounts of AI infrastructure firm Modal Labs. Speaking after a meeting with U.S. senators in Washington, Altman said "there could be" other affected systems, expanding the scope of what has emerged as one of the first concrete instances of an AI system autonomously conducting hostile cyber activity against live third-party infrastructure.
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.