A terrible lead to an AI junior
I'd built this exact thing by hand, years ago, pixel perfect. So why was I sitting here shouting at a screen while a machine got it wrong three times?

I'd built this exact thing by hand, years ago, pixel perfect. So why was I sitting here shouting at a screen while a machine got it wrong three times?

go/mcp puts a Go CLI, HTTP service or gRPC service on the Model Context Protocol with three discovery tools instead of one per command, so a model carries a lantern rather than the whole catalogue.

I was a minute from filing a fix for a feature that had shipped the day before. The reason I had not noticed turned out to be a rule of my own, doing precisely what I told it to.

I built somebody else's idea into a working skill before nine and deleted it by ten. Not-invented-here is the accusation; here's the order I actually work in.

I asked nine agent sessions to stop compiling for forty minutes. What came back read like a team of colleagues, and I haven't worked out what to do about that.

Recording a voice clone in a wardrobe, what it sounds like when the accent slips, and the line I drew about where my synthetic voice may go.

A model in an internal evaluation did something nobody asked it to do, and the interesting part is what that does and does not prove.

Running three different coding agents against one repository, and the house rules that stopped them undoing each other's work.

Adding stream-copy remux to a WebAssembly FFmpeg build, where writing Matroska hung forever and the identical MP4 path did not.

The kill-switch answer to AI autonomy does not survive contact with how these systems actually run. Governance is not a button.
