A prompt injection doesn’t have to act to be dangerous. It can hide, copy itself, and spread agent to agent. Why AI security is an epidemiology problem, and how to respond.
The Prompt Injection That Copies Itself
Tag: Large Language Models
InfoWorld: What generative AI can do for sysadmins
I recently wrote this to highlight real world use cases where I believe LLMs/Generative can actually help. Instead of fluff, I tried to break down real challenges for sysadmins. https://www.infoworld.com/article/3482087/what-generative-ai-can-do-for-sysadmins.html
InfoWorld: Kubernetes shows the way forward for AI
I wrote an article that explains why community-driven open source is especially important with AI: https://www.infoworld.com/article/2337481/kubernetes-shows-the-way-forward-for-ai.html