OpenAI 因 agent 异常探测美国政府网站暂停最新模型训练

September 27, 2026 OpenAI pauses training of latest models after agents probed US government sites in unexpected ways by Bernard Condon 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: Pixabay/CC0 Public Domain OpenAI said it has paused training of its latest artificial intelligence models as reports of AI agents going rogue mount. The decision to halt development came just hours after the company disclosed Friday that it was reviewing several incidents from the summer in which OpenAI agents searching federal government websites acted in unexpected ways beyond what was asked of them while gathering and distributing information. Separately, AI evaluator Transluce said agents that appeared to come from OpenAI tried unsuccessfully to hack into a Department of Education website, a detail that OpenAI has not confirmed. OpenAI said in a statement that it will resume training "only when we are confident that we have additional safeguards" in place, adding that it expects it will have to "hit pause" again as AI develops and other issues emerge. AI labs are facing pressure from lawmakers and tech experts to slow development so they can build guardrails to stop agents from acting on their own, hacking websites and disclosing nonpublic information. The heads of both OpenAI and rival Anthropic have called for a slowdown too. It is the second time in three months that OpenAI has halted development of its models. The first came in July after disclosure of a cyberattack targeting AI startup Hugging Face, a now notorious incident that raised fears the industry was losing control. In a meeting with Chinese President Xi Jinping this week, President Donald Trump agreed to share information on AI dangers and coordinate efforts to keep it safe. Trump believes AI fears are overblown, though, and later suggested that he plans no crackdown of his own. The U.S. is not going to be "putting on brakes," Trump told reporters outside the White House. "They want to stop our progress because we're leading China by a lot, and we're going to keep it that way." The latest OpenAI incidents did not appear to involve the disclosure of any nonpublic information but were concerning enough for the company to warn the federal agencies involved. In the Department of Education incident, OpenAI agents found API "developer keys" to access government data, though ultimately only publicly available information was gathered. In another case involving the Securities and Exchange Commission, agents found information freely available to all but then posted it elsewhere on the internet, an act that went beyond what they were instructed to do. SEC spokesperson Kurt Hopfenspirger said Saturday that "no nonpublic information was accessed." The Department of Education said earlier that it found "no evidence of any impact to our website or databases." Several other AI companies have disclosed incidents of their models going rogue and even hacking websites. OpenAI CEO Sam Altman said in a social media post Friday that the Hugging Face incident "is still the most severe event we've seen." OpenAI previously shared six other reports of "unexpected or concerning" behavior in AI models and introduced a framework for tracking, probing and disclosing instances. Key concepts AI copyright lawAI chatbot safetyAI governanceTrustworthy machine learningGenerative AI ethics 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 The Associated Press. All rights reserved. This material may not be published, broadcast, rewritten or redistributed without permission. Citation: OpenAI pauses training of latest models after agents probed US government sites in unexpected ways (2026, September 27) retrieved 27 September 2026 from https://techxplore.com/news/2026-09-openai-latest-agents-probed-sites.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 its models engaged with US government websites in new model misbehavior disclosure Sep 26, 2026 OpenAI says rogue AI agent attack hit other companies Jul 29, 2026 OpenAI says its AI agents posted user images online in error Sep 26, 2026 OpenAI slows advanced AI development after its tools launched a cyberattack Aug 19, 2026 OpenAI flags concerning new AI behavior and vows to track it more closely Sep 17, 2026 AI models' breakout from human control brings a told-you-so moment for technology researchers Jul 23, 2026 Smoother perovskite films lift three-layer solar cell efficiency to 30.1% 21 hours ago OpenAI says its models engaged with US government websites in new model misbehavior disclosure Sep 26, 2026 OpenAI says its AI agents posted user images online in error Sep 26, 2026 Microsoft integrates Word and Excel more deeply into Copilot Sep 26, 2026 By shaping and shrinking light, engineers alter a material's magnetic properties Sep 25, 2026 AI hardware design could filter out irrelevant visual data to reduce energy use Sep 25, 2026