▽Schneier on Security ●02/06 02:33 On Generative AI SecurityMicrosoft’s AI Red Team just published “Lessons fromRed Teaming 100 Generative AI Products.” Their blog post lists “three takeaways,” but the eight lessons in the report itself are more useful:Understand what the system can do and where it is applied.You don’t have to compute gradients to break an AI system.AI red teaming is not safety benchmarking.Automation can hel