On: AI coding has made CI a bottleneck, so we reworked ours to keep up

[aprilthird2021]

AI makes a lot of drudgery type coding tasks a lot easier (think code migrations, etc.)

But actually coming up with, testing, and rolling out loved new user features. AI isn't that good at that and we can't really "prompt" that out of it as easily as we can prompt a py2 to py3 conversion of old code

[Rapzid → aprilthird2021]

I'm noticing this. Net new features need a ton of extra human input vs cleanup, bug fix, or translation tasks.

Models are just terrible at system design. Which makes sense as they are largely trained on "tasks" right?