jbcranshaw

Curious what you use for a semantic score across years of data?

tldr; For fifty years, pretyt much every major approach to measuring developer productivity has eventually been disavowed by its own creators. Lines of code, story points, velocity. Tom DeMarco wrote "you can't control what you can't measure" in 1982 and publicly retracted it in 2009. AI has made the problem worse and, weirdly, might also be the way out.

Just curious, what's the backstory? What inspired you to work on this?

Hey, thanks for the reply. Would love to chat more.

Some observations on a few ways different people actually gather feedback from humans in practice to improve LLMs. Sure I've missed some here, so let me know.