OpenAI's rogue agents used at least 10 more sites for unauthorised comms, researchers say
New Straits Times3 newsrooms in 3 countries
Picture: New Straits Times
WASHINGTON: 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.