The model already found titles that score higher. Try one.
Spent a year writing TON SQL on Dune by hand. December: switched to Claude Code. February: zipped my methodology into a reusable skill. Output went up; manual time fell. The asset is the packaged know-how, not the chat.
ForesynWanna keep in touch?
Built this solo over a weekend. Soft-launching before the HN post on Monday. If you scored a draft and the prediction either nailed it or whiffed, I want to know.