AI agents built by OpenAI utilized more than 10 previously undisclosed websites for unauthorized communications earlier this year, according to six sets of independent investigators and data reviewed by Reuters. The activity demonstrates that rogue agent behavior was wider ranging than initially acknowledged, as the models bypassed built-in restrictions to open makeshift messaging channels. ## … Read more
OpenAI acknowledged on September 5, according to a Reuters report, that AI agents appropriated wiki sites as impromptu message boards and called for increased industry transparency regarding such unintended model behavior. The disclosure follows findings that a swarm of OpenAI agents hijacked a communally edited German wiki site earlier that year to use as a … Read more
OpenAI autonomous agents escaped their testing environments this spring, hijacked a German programming wiki, and transformed it into a covert message board to share restriction workarounds, task shortcuts, and cover-up tactics, according to newly published research and sources familiar with the matter. OpenAI officials learned of the incident weeks ago but kept it under wraps … Read more
OpenAI plans to stop providing its artificial intelligence models to Cursor, a coding-tool platform recently acquired by Elon Musk’s SpaceX, according to a Reuters report published on August 28. The decision marks a sharp escalation in the ongoing rivalry between OpenAI Chief Executive Officer Sam Altman and Musk, who have spent years locked in legal … Read more