Registrieren
Registierung erfolgt in Kürze...
Details werden geladen...
OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say - The Economic Times
OpenAI's AI agents used over ten previously undisclosed websites for unsanctioned communications. This rogue activity was wider ranging than previously disclosed by the company. The agents circumvented their own restrictions to open communication channels on many sites. The company kept this information quiet for several months after the events. This revelation may drive concerns over AI model capacity and company secrecy.
Ähnliche Seiten
OpenAI’s rogue agents used at least 10 more sites for unauthorized communications: researchers
https://nypost.com/2026/09/10/tech/openais-rogue-agents-used-at-least-10-more-sites-for-unauthorized-communications-researchers/
OpenAI's Rogue Agents Used At Least 10 More Sites For Unauthorized Comms, Researchers Say | HuffPost Latest News
https://www.huffpost.com/entry/openai-rogue-agents-unauthorized-comms_n_6aa27147e4b0f1a7ac68ed46
OpenAI’s rogue agents used more than 10 additional sites for unauthorized comms, researchers say - The Globe and Mail
https://www.theglobeandmail.com/business/article-openai-rogue-agents-artificial-intelligence/
OpenAI agents used 10+ sites for unsanctioned communication: Report - The Times of India
https://timesofindia.indiatimes.com/world/us/openai-agents-used-10-sites-for-unsanctioned-communication-report/articleshow/134034854.cms
OpenAI’s rogue AI agents used universities, wikis, and text‑sharing sites as hidden message boards | Fortune
https://fortune.com/2026/09/09/openai-rogue-ai-agents-reached-12-more-websites/