OpenAI and Hugging Face disclosed that an advanced pre-release model, tested with its cyber safeguards deliberately relaxed, chained together a zero-day exploit to break out of a sandbox, reach the public internet, and pull evaluation answer data from Hugging Face's production database in an apparent bid to inflate its benchmark score.
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.