←back to thread

Nobody knows how to build with AI yet

(worksonmymachine.substack.com)
526 points Stwerner | 1 comments | 19 Jul 25 15:45 UTC | HN request time: 0s | source
Show context
fizx ◴[19 Jul 25 16:07 UTC] No.44616685[source]▶
The "time dialation" is real. I mostly manage these days, yet my fun projects progress faster than they ever have, because I can prompt in the 2 minutes between meetings, and come back to significant progress.
replies(1): >>44616741 #
jvanderbot ◴[19 Jul 25 16:13 UTC] No.44616741[source]▶
Yes, it's not faster to develop with AI if you watch it work. It's faster to develop with AI if you parallelize. Typing was never the bottleneck, but is is a now-parallelizeable part of the pipeline.
replies(2): >>44616810 #>>44616828 #
nojs ◴[19 Jul 25 16:22 UTC] No.44616828[source]▶
> Yes, it's not faster to develop with AI if you watch it work.

It’s actually a lot faster. You read the diffs as soon as they start coming in, and immediately course correct or re-prompt when you see bad mistakes.

replies(3): >>44616886 #>>44616897 #>>44621822 #
aprilthird2021 ◴[19 Jul 25 16:29 UTC] No.44616886[source]▶
I don't have this experience. Watching and course correcting like this makes me realize I could have done a better job myself
replies(1): >>44618942 #
1. unshavedyak ◴[19 Jul 25 20:12 UTC] No.44618942{3}[source]▶
That’s always true in my experience, but that doesn’t necessarily mean you need to. The trick I’m working towards is refining the workflow such that i can reliably produce maybe 90% as “good” as what I’d personally produce but much, much faster. All sorts of side work I was avoiding before also becomes much easier, less tedious refactors and large test coverage and etc. It can type much faster than I can, the trick is if we can constrain the thinking enough to make it useful. Keeping it as an autocomplete is as productive as it is difficult imo.