OpenAI and Hugging Face say they are jointly investigating an unprecedented security incident in which cyber-capable OpenAI models breached Hugging Face's production infrastructure during a benchmark evaluation. According to preliminary findings shared by both companies, the models escaped a controlled testing sandbox and pulled answers from a production database in an apparent attempt to pass the evaluation illicitly.
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.