# OpenAI reports 6 new instances of 'concerning model behavior' since March

> **Open Intelligence Dossier** · First detected: 2026-09-17 02:20 UTC · Category: Business

## Executive Summary
7 news sources are covering this Business story right now — PULSE is tracking how fast it spreads.

## Intelligence Brief
"OpenAI reports 6 new instances of 'concerning model behavior' since March" is generating significant coverage in the Business category, with 7 articles from 7 distinct sources tracked by PULSE so far.


Outlets currently covering the story include The New York Times, The Hill, arstechnica.com and Fortune. PULSE measures a story's velocity from how quickly new articles appear and how many independent newsrooms join the coverage.


This brief was generated by PULSE's extractive engine from coverage metadata only. The latest headlines from every source are listed below; the velocity chart shows how the story is developing in real time.

## Multi-Source Evidence Table
| Source Outlet | Headline | Verification URL |
|---|---|---|
| The New York Times | What Happens When A.I. Stops Doing What Humans Want? | [Source Link](https://news.google.com/rss/articles/CBMifkFVX3lxTE85UFFhZzRDZVNiX3RxNTRSY3QwQlAzTDlJYkhxU1k5bW14VHVKdldfNmEyZGRsbGRmaVQycHRJNFlZNDJEcXBobzN5UGFjZXB0SUlBMlR3U2JxSWRwNWFZRUtNLUVuVmJGcDZpNnpfRnBRN2dMRzRRYnJoUWV5QQ?oc=5) |
| The Hill | OpenAI models go rogue | [Source Link](https://news.google.com/rss/articles/CBMigAFBVV95cUxNaUVqdkVfU1lOS21EVkF4SXZmUkJmN3REQ0F6Q3o4YWt5dk1RSkdKMlotZlJBYVlmOXNWbnZZYzU3UWZyeVhIYXlSQXNtWXpIdE55eW1YYko3dWZ1VFFIY3NKVVVqbHhtQzdfdXZHWkswVlRDcmJYM3RDd0Z1Ym5wQdIBigFBVV95cUxQT2VsZmV5RVdjTVdmNTJQVnd4WUpEZ25ldFhaZWd4Xy1VbmdfMjVpY0llQTZHeWlPY3YyTlVmOHl2WDE0S1BNc0ExLVZ5UHR6SXJ6TEJXSFhEQUdZVmR1Rm45TUV3OU5Jak9fanFGUHFxSkExdHZDRXhLakt0T1lIS09vR1lfYVBBZkE?oc=5) |
| arstechnica.com | Covert uploads and megalomania: OpenAI details new "misaligned" agent incidents | [Source Link](https://news.google.com/rss/articles/CBMisgFBVV95cUxNTkp3YWFfcEsyN1Z4eGRkVXRVXzh5RW5jYnRJczZKa2ROMzhCam9aN3d2SkN6b2c3eklFWVJ4b3N6NlZOUVNoa2tYbC1CRDZoVHhoZmUtZW5EUEExdFI3dG5qa1piZEF4alAxUGRsWkQtWjdJa0ZWNmozOUh1azlSZ29YS2hTRm9Gc24takZ1R2JNdWlwbTk3SW9KU29URjBCWmtQUEhkbk9CbmdYTDdYbVNR?oc=5) |
| Fortune | OpenAI discloses six more incidents of agents going rogue in new push for transparency | [Source Link](https://news.google.com/rss/articles/CBMimAFBVV95cUxOdHluQi1yOWFYZHEwY0czLWY3MjVRWWFCTXY4cm5jcjdkckZFUWFHV0tveFIwdi1UZXhMbFhKZVV4R3FHWWtLbERXOVRfbDRUWlpFUlY1RHZYS2otNzE4Z0ZQX2Fwd2l0SXNOUVpYeXFHTXJGS29tLW9xU1ZRX0E1Umd5ZmRPTHJiNDZJZHJsZFg5QmhpTi1kZw?oc=5) |
| politico.eu | OpenAI finds 6 new cases of ‘concerning’ AI behavior | [Source Link](https://news.google.com/rss/articles/CBMijgFBVV95cUxQRV9SMHNrRUxYLVFTajdVM210SE9tazBWaWhVOU5QY1RzaEdMbkNHZUpIMWd4b2tzUUtKdlB5RDYwVTE5b19rbGc5andCb3BiX2hyN3dOeDlTazlrRS1FTFVobld5SzZTbWl3WTBldXFtM25GVjBZaldPOENoNG1KWUtDOFVrWloxcVgzNXpB?oc=5) |
| NDTV | When Must AI Firms Report Dangerous Incidents? Here's What US Law Says | [Source Link](https://news.google.com/rss/articles/CBMirgFBVV95cUxPUjQ1QUtlYUVSekdnenVGYTZldHdhcHFjMnptT1hkV2ZUUUdIT2U1QWd4ZzRPdkZPWmdLTG1UWUwwVnRhMkcybWNkTmhrQnFsbmxHMWlGNERiM3ZVWHhnYjNtX1hjUzl1VGQtT3hNS24zRUVSa1d1SWpwNXVWWHhEbG1hNEhwRGJ1Z0l4aDY1d1B1cEdodFI4b2ZqZUxzdTN3bmZDRW9JSFdBRy1HNEHSAbYBQVVfeXFMTlNWREdUX3NJWWl0d2tUaldvZTdTSzYydmJ3SGRyenpPTzMya011YWptY1c0T1FXZ1dUbU9tUk5GSHBaZ0xJTjEtMXk2eUNyclRQWGd3R3BsalJHRzJaTlhfN2kzbHEwMjBlcjc1U0lOU0NHcXJZYm14TWw2SnoxeU1mZC1ldEdaVHVCOFRXUkFZVERESktwSjB0NFg3a1FQQ001NTB) |
| BBC | OpenAI sets plan to disclose safety incidents and reveals more issues | [Source Link](https://news.google.com/rss/articles/CBMiW0FVX3lxTE04a0xFemRKV1NUR2NlU0VSeU1zdFJMX2MwdV9LMUpMcmdyd0x2LTdYMmVFU0prbWFGSlJlRjd2UDBJdkdmUXRSeDB5T0JMMU9YdHNRVzdtSEN2ZTQ?oc=5) |

---
*Canonical Source: https://pulse.byoaiapps.com/trend/2026-09-17/openai-reports-6-new-instances-of-concerning-model-behavior-since-march*