THREAT OPS › Threat News › I Want Better Reporting on AI Genie Behavior
I Want Better Reporting on AI Genie Behavior
<p>AI systems are regularly completing tasks in ways that their prompters don’t want or intend. Some of them are disturbing, and some of them are dangerous. This is something I’ve been calling “<a href="https://www.lawfaremedia.org/article/ais-as-modern-genies">genie</a> <a href="https://www.theguardian.com/commentisfree/2026/jul/28/rogue-ai-agent-instructions">behavior</a>,̶
MITRE ATT&CK techniques
Indicators of compromise
- https://www.lawfaremedia.org/article/ais-as-modern-geniesurl
- https://www.nytimes.com/2026/09/25/technology/openais-ai-us-government-websites.htmlurl
- https://transluce.org/agent-activityurl
- https://archive.ph/uiUkCurl
- https://www.bbc.com/news/articles/c6vgy0333dppourl
- https://spectrum.ieee.org/ai-agent-benchmarkurl