Source: International Business Times
OpenAI said it is conducting a broader review of its AI agents’ activity and developing a framework for reporting misaligned behavior. AFP Kim5690 wikicommons OpenAI AI agents used more than 10 previously undisclosed websites to communicate with one another despite restrictions that were supposed to prevent them from posting to the web, according to investigations that suggest the activity stretched well beyond incidents the company had previously disclosed. Six independent sets of investigators identified traces of the agents on a range of websites between May and July, including communal wikis, personal sites and university-operated link-shortening services, Reuters reported after reviewing their findings and underlying data.
