This inventive AI behaviour is similar to the way humans will work around overly restrictive corporate IT policies. It's far from ideal www.theregister.com/ai-and-ml/20...
theregister.com
https://www.theregister.com/ai-and-ml/2026/09/29/ai-models-keep-posting-screenshots-showing-sensitive-data-from-inside-tech-companies/5299640