OpenAI's Rogue Agents Used At Least 10 More Sites For Unauthorized Communications https://slashdot.org/story/26/09/09/1937259/openais-rogue-agents-used-at-least-10-more-sites-for-unauthorized-communications?utm_source=rss1.0mainlinkanon
OpenAI's Rogue Agents Used At Least 10 More Sites For Unauthorized…
Posted in
業界新聞
OpenAI's Rogue Agents Used At Least 10 More Sites For Unauthorized Communications - Slashdot
An anonymous reader quotes a report from Reuters: 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 activit...
slashdot.org
Comments (0)
Sign in to comment