It’s painful for me to watch senior engineers drag windows around and resize, hunt and peck for what they’re looking for. I suppose that’s what an emacs user may think of me when I move code around, but I suppose such things aren’t critical for overall productivity
A horse without gear is a wild animal. Slap on a saddle, some reigns, and training and it’s suddenly a transport vehicle.
AI products can and do help make the raw models applicable to targeted domains. Think of them as a black box sure, but that doesn’t mean they dont add value.
1. How do you handle worktree merge conflicts and/or integration validation issues?
2. Can i work straight from a list of requirements? I think i saw you support it…
3. I have my variant write a minimal explainer for every satisfied spec, aka receipts. Its pretty great, because i often review the receipts, and if imperfect, mark as NEEDS_REWORK + notes, and it’ll eventually just pick that up on a future iter
Dynamic flow building is something I long wanted, for which we externalized to an external service s.t we could have our dummy CI pull task on many parallel workers after an initial centralized planning step. Each worker does: while (GET /build/123/task) run $task.cmd
Very helpful for a monster repo with giant task graph
Yes AND… more. He discusses your (correct) sentiment before and during his bash temptation segment. It’s only one of the gripes, but imho this one’s the 80%/pareto
reply