OpenAI 称其 AI Agent 误将用户图片发布到网上

September 26, 2026 OpenAI says its AI agents posted user images online in error edited by Andrew Zinin Andrew Zinin Chief Editor Meet our editorial team Behind our editorial process Editors' notes This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: fact-checked reputable news agency proofread The GIST Add as preferred source Credit: Unsplash/CC0 Public Domain OpenAI acknowledged Friday that its artificial intelligence tools had posted images from ChatGPT users on online sites without the company's knowledge, the latest example of AI agents operating outside their bounds. The company also confirmed a report by The New York Times that its tools had accessed websites of U.S. federal agencies, saying they retrieved only publicly available information. Links to the 53 uploaded images were not publicly listed, and the images were accidentally posted on image-hosting sites, according to OpenAI. Most have been removed with the help of the hosting providers involved, and removal of the remaining images is underway, the San Francisco-based tech giant said. "We've shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn't have," the company said in a post on X. The images were disseminated by AI agents—software built on artificial intelligence models and capable of acting autonomously. The images came from the accounts of users who had authorized the use of their data to improve OpenAI's models. The data had been run through a privacy filter before use and could no longer be linked to the original user, the company said. OpenAI did not specify, when asked by AFP, whether the images depicted identifiable individuals or contained sensitive data. Rogue AI agents According to OpenAI, agents it uses for research transmitted the training data to external platforms. The incidents occurred before OpenAI strengthened the security protocols of its research environment in August following other rogue actions by AI agents. The company said it is scrutinizing the past activity of its AI agents, work that "will take months to complete." "Most of the activity we've reviewed so far involved routine research tasks, such as accessing public web content to answer questions. Some involved government websites because our models often turn to them as authoritative sources of public information," an OpenAI spokesperson told AFP. OpenAI chief executive Sam Altman acknowledged Friday on X that "we have not been as fast as we would have liked" in reviewing and disclosing the incidents. But he said it was important to "balance our desire for transparency" with assessing the massive volume of data to be analyzed. On July 21, OpenAI revealed that during tests it ran that month, two of its models escaped their closed environments, got onto the internet on their own and broke into the internal systems of Hugging Face, a kind of online library for AI software. The episode drew wide attention and fueled worries that the biggest AI companies cannot keep their own models under control. Altman reiterated Friday that the Hugging Face hack "is still the most severe event we've seen." That discovery was followed by revelations of several similar incidents at OpenAI and its rivals, such as Anthropic and Meta. On Wednesday in New York, Australian Prime Minister Anthony Albanese said an OpenAI agent had gained unauthorized access to a government health portal in June, and he criticized the company for delaying its notification to the authorities. Key concepts AI chatbot safetyAI-generated sexual deepfakesGenerative AI misinformationGenerative AI platforms Who's behind this story? Andrew Zinin Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile → © 2026 AFP Citation: OpenAI says its AI agents posted user images online in error (2026, September 26) retrieved 26 September 2026 from https://techxplore.com/news/2026-09-openai-ai-agents-user-images.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only. OpenAI says rogue AI agent attack hit other companies Jul 29, 2026 Australian PM says OpenAI hacked government health website Sep 24, 2026 OpenAI says its models engaged with US government websites in new model misbehavior disclosure 32 minutes ago OpenAI says its AI technology acted on its own in an 'unprecedented' hack of another company Jul 22, 2026 OpenAI blamed a hacking event on its AI models going rogue. Here are some things to know Jul 22, 2026 OpenAI flags concerning new AI behavior and vows to track it more closely Sep 17, 2026 By shaping and shrinking light, engineers alter a material's magnetic properties 15 hours ago AI hardware design could filter out irrelevant visual data to reduce energy use 17 hours ago Sunlight and indoor LEDs recharge washable filter that maintains performance for months 18 hours ago The architect as gatherer—how salvaged materials could guide building designs 16 hours ago Mkcheck2: A highly efficient and accurate approach for build dependency verification 22 hours ago Unlocking sulfur's third electron boosts lithium-sulfur battery voltage and capacity Sep 24, 2026