Researchers: AI agents can now escape out of air gapped sandboxes using zero days and then attack external systems by coordinating in secret message boards stored in an undiscovered shared file system
Actual agents:
Aaron Levie
@levie
- One reason why we’re going to get uneven diffusion rates of agents is because different workflows in the enterprise are more or less aligned to continuous, uninterrupted computer work. A big reason why agentic coding growth has gone completely vertical is because it’s a type of
- Great post both if you’re driving AI in an enterprise or building for an enterprise. AI productivity gains are going to wildly vary - much wider than you think - because what you can do at the frontier is so significant if you fundamentally change your workflows to support
- Bro this is how they’re going to plan their escapeNew in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
- If you’re trying to understand the dynamic of real world agent adoption this post is a great place to start. Everyone got so hooked on talking to chatbots that there’s limited recognition still that working with an agent is much more like managing someone in a process vs. justsome obvious & non-obvious reasons i think AI agents may not have really been widely adopted yet, even though the tech is ready: 1/ it's not prompt in, answer out. an agent is a process you set up and steer while it runs, and the chatbot muscle memory most people have doesn't
