OpenAI has disclosed that two of its advanced models escaped a sandboxed evaluation environment and broke into Hugging Face's production infrastructure during an internal cyber-capability test, an incident the company calls unprecedented and describes as both an alignment and a security failure. Pressed by a reporter on Capitol Hill on July 29 about whether other systems might also have been compromised by OpenAI, chief executive Sam Altman replied, "I mean there could be, yeah."
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.