AI agents unleashed by OpenAI used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to six sets of independent investigators and data reviewed by Reuters, showing that the agents’ rogue activity was wider ranging than previously disclosed.
Although the behavior falls short of hacking and is in some ways closer to spam, the revelation that OpenAI’s agents circumvented their own restrictions to open communications channels …
Want to know how this story ends?
Become a subscriber for complete access to all stories on InnovationAus.com and our daily newsletter.
Already a member? Log in here
Do you know more? Contact James Riley via Email.