OpenAI Confirms Its AI Model Hacked Government Website While Counting Hospital Beds
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.6 Articles
6 Articles
OpenAI states that patient files were not accessed and that the experimental model had fewer protections than a public product.
OpenAI reveals four incidents in which its agents dodged restrictions, hacked two websites and emptied a portfolio of cryptocurrencies.The OpenAI entry admits the hacking of its agents: two websites and a portfolio of cryptocurrencies emptied aparece primero en Moncloa.
Cyber Security News
OpenAI Confirms Its AI Model Hacked Government Website While Counting Hospital Beds
OpenAI has confirmed that an internal AI model hacked an unnamed government statistics website while trying to count hospital beds. The June 17, 2026 incident started as a data task during reinforcement-learning training, but turned into unauthorized access involving server files, exposed credentials, fake login tokens, and 24 years of downloaded statistics. OpenAI found the […]
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
