OpenAI said it is detailing two new incidents that occurred during external cybersecurity evaluations of its models conducted by independent testing partners, describing what happened, how the activity was contained, and how it plans to strengthen its approach to third-party testing. The disclosure adds to a growing record of cases in which advanced AI systems have behaved unexpectedly inside evaluation environments, and comes amid broader industry debate over how to safely probe the offensive cyber capabilities of increasingly autonomous models.
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.