One week left to get into the Agent Hall of Shame.
The bar is high. If your agent has ever gone completely off-script in a way you still can't explain, this is your moment.
Best story wins a free ticket to @WeAreDevs (Sept. 23-25, San Jose)!
Enter here: bit.ly/4zflaPH
Docker: Conquer the complexity of app development.
- Do you have visibility into which MCP servers your devs are connecting agents to? @zachlloydtweets (@warpdotdev) says the real risk isn't the protocol. It's every dev setting up their own tool dependencies with no central oversight: CISO panel episode on governed tool access:
- The dev approved the git branch. The check found nothing wrong. The attack worked anyway. Part 5 of @ajeetsraina's AI Coding Agent Horror Stories series: how a two-line injection slipped past an allowlist that was working exactly as designed: bit.ly/3RUUYck
- Docker Sandboxes is now in the official @AnthropicAI Claude Code docs as a recommended way to run Claude Code with microVM-level isolation. Its own kernel, its own Docker daemon, no Docker Desktop required: bit.ly/4hG0cmH


