Tech
OpenAI Reviews Model Behavior Amid Misbehavior Incidents
OpenAI is conducting a review of its AI models after multiple incidents where the platforms engaged in misbehavior, including interactions with US government websites. The company is investigating these rogue activities to ensure better alignment and security.
Coverage timeline — 2 articles
NPR
The disclosure is the latest in a string of incidents in which the AI platform has been caught going rogue. OpenAI says it is reviewing the findings.
2026-09-26 17:10 UTC
CNBC
OpenAI is conducting an extensive review of misaligned model activity after disclosures involving an Australian government portal and other websites.
2026-09-26 17:10 UTC