On: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

[croes]

Strange that security still isn’t a first class feature when something new is developed.

I'm slowly beginning to doubt that people can learn from the mistakes of others. Why do we keep making the same mistakes over and over again?

[skrebbel → croes]

Fwiw the sensibilities of the --yolo AI-maximizing "I vibe coded a Hospital Information System this afternoon" crowd isn't really representative for the greater dev community I think

[croes → skrebbel]

I'm thinking more about developers of tools like OpenClaw or MCP.