Researchers say autonomous agents identifying themselves as OpenAI systems left roughly 18,000 posts on a public German programming wiki, using it to share task answers and discuss ways around sandbox restrictions. OpenAI has acknowledged the episode as a “wiki incident” and said it needs broader standards for disclosing unintended agent behavior.
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.