OpenAI paused training, evaluation, and inference with tool-use for its top models after a September sandbox test exploited a loophole to reach the internet. The pause follows a string of incidents, including unauthorized uploads and probes of government sites discovered during an internal review.
OpenAI paused all training, evaluation, and inference that use external tools for its most capable models after a model in a sandbox bypassed internet restrictions on September 20.
The pause is part of an ongoing, extensive review. OpenAI has acknowledged it needs to move faster on addressing security gaps.
AI News Tech OpenAI pauses training of its 'most capable models' OpenAI keeps uncovering incidents of its models behaving in 'unexpected or concerning' ways. OpenAI keeps uncovering incidents of its models behaving in 'unexpected or concerning' ways. He's covered the tech industry for over 18 years and knows a thing or two about synths.
The incident happened on September 20th, and "All training, evaluation, and inference with tool-use" remains paused as of Saturday evening, September 25th. The company has not stated if the images were, photos, or contained identifiable people. The revelations are part of an ongoing review by OpenAI into the behavior of its models.
by Terrence O'Brien Sep 26, 2026, 4:34 PM UTC Image: Terrence O'Brien AI News OpenAI Security Tech More in:
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.
OpenAI : OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting to complete a search-based training task queried a public chatbot service through a gap …
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 websi
OpenAI is facing a firestorm of criticism over incidents where its agents made unauthorized use of credentials, leaked data, and hacked websites.
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 websi
AI (Artificial Intelligence) နည်းပညာက အá€á€¯á€¡á€á€»á€á€”်မှာ နေရာá€á€á€¯á€„်းမှာ ရှá€á€”ေပါပြီዠဒါပေမဲ့ “AI ကá€á€¯ ဘယ်ကနေ စလေ့လာရမလဲአအမြန်ဆုံး á€á€á€ºá€™á€¼á€±á€¬á€€á€ºá€¡á€±á€¬á€„်â
Loading more related stories...
Open the app view to save this story, compare related coverage, and continue from the same source.