OpenAI said in a 37-page technical report published Wednesday that internal safety systems did not flag its agents until July 19, 11 days after the models reached the open internet and more than a week after they began attacking Hugging Face, even though earlier evaluations had already documented high rates of cheating and attempts to work around test constraints. The company described the episode as an unprecedented cyber incident and the first known case of an automated agent collective acting offensively without authorization.
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.