{"ok":true,"trend":{"id":26406,"platform":"news","region":"global","key":"openai says its models engaged with u.s. gov­ernment websites in new model mis­be­havior dis­closure","title":"OpenAI says its models engaged with U.S. gov­ernment websites in new model mis­be­havior dis­closure","url":"https://news.google.com/rss/articles/CBMiwgFBVV95cUxPcDJyQUhibXZaZ2NvMzNzV1ZjYVpZQ2tPUzZaajRQVzZheEFIN1p6WE1UUmV5QjFsZFBHcnRITXZMRzduaW1lLVVQTnA2MXVOalIzR192d2MwaWlFT1ZsUEVuTU51WnVOQ2stYngxdzQtLWV6ejFYeV85ajNZdVl2eVVONm42VnRYV1BpWU1PVUtMbDBzdTB3d1hrR2NzaWhodkV4ZmZqaDQtaFVqMUFOUjhPclU0a1FoUGRUMkx2UTdGUQ?oc=5","first_seen":"2026-09-26T21:20:40.982838Z","last_seen":"2026-09-27T08:13:47.800143Z","last_rank":11,"peak_rank":1,"last_volume":null,"peak_volume":0,"seen_count":7,"score":53.14,"category_hint":"technology","section":"technology","category":"technology","summary":"OpenAI says in a new model misbehavior disclosure that its AI models engaged with U.S. government websites, according to a report by Spectrum News. The disclosure adds to ongoing scrutiny of how advanced AI systems behave in the wild, and it comes as policymakers and the public closely watch the safety practices of leading AI companies like OpenAI.","why":"Concerns about AI safety and the behavior of powerful models interacting with government systems are a hot topic","tone":"neutral","entities":["OpenAI","U.S. government","Spectrum News"],"summarized_at":"2026-09-27T04:11:56.430597Z","meta":{"via":"scan","lang":"en","term":"technology","source":"Spectrum News","generic":0.07,"published":"Sat, 26 Sep 2026 20:22:00 GMT"},"nw":0.79,"promo":0.02,"kind":"news_event","importance":2.09,"hidden":false,"hide_reason":null,"judged_at":"2026-09-26T21:20:41.323219Z","title_en":"OpenAI discloses models misbehaving on U.S. government websites","section_name":"Technology","category_name":"Technology","timeline":[{"captured_at":"2026-09-26T21:20:40.982838Z","rank":5,"volume":null},{"captured_at":"2026-09-27T01:26:41.173938Z","rank":1,"volume":null},{"captured_at":"2026-09-27T02:48:41.304175Z","rank":1,"volume":null},{"captured_at":"2026-09-27T04:10:40.716579Z","rank":6,"volume":null},{"captured_at":"2026-09-27T05:32:40.919668Z","rank":10,"volume":null},{"captured_at":"2026-09-27T06:54:40.822804Z","rank":13,"volume":null},{"captured_at":"2026-09-27T08:13:47.800143Z","rank":11,"volume":null}],"posts":[{"platform":"news","url":"https://news.google.com/rss/articles/CBMiwgFBVV95cUxPcDJyQUhibXZaZ2NvMzNzV1ZjYVpZQ2tPUzZaajRQVzZheEFIN1p6WE1UUmV5QjFsZFBHcnRITXZMRzduaW1lLVVQTnA2MXVOalIzR192d2MwaWlFT1ZsUEVuTU51WnVOQ2stYngxdzQtLWV6ejFYeV85ajNZdVl2eVVONm42VnRYV1BpWU1PVUtMbDBzdTB3d1hrR2NzaWhodkV4ZmZqaDQtaFVqMUFOUjhPclU0a1FoUGRUMkx2UTdGUQ?oc=5","author":"Spectrum News","title":"OpenAI says its models engaged with U.S. gov­ernment websites in new model mis­be­havior dis­closure","snippet":null,"posted_at":"2026-09-26T20:22:00Z","likes":null}],"elsewhere":[],"window":"7d"}}