←back to thread

AI coding and the peanut butter and jelly problem

(iamcharliegraham.substack.com)
121 points tylerg | 2 comments | 11 Apr 25 21:26 UTC | HN request time: 0s | source
Show context
zahlman ◴[11 Apr 25 22:47 UTC] No.43659511[source]▶
Okay, but like.

If you do have that skill to communicate clearly and describe the requirements of a novel problem, why is the AI still useful? Actually writing the code should be relatively trivial from there. If it isn't, that points to a problem with your tools/architecture/etc. Programmers IMX are, on average, far too tolerant of boilerplate.

replies(5): >>43659634 #>>43659667 #>>43659773 #>>43660939 #>>43661579 #
1. larve ◴[11 Apr 25 23:07 UTC] No.43659667[source]▶
Useful boilerplate:

- documentation (reference, tutorials, overviews) - tools - logging and log analyzers - monitoring - configurability - unit tests - fuzzers - UIs - and not least: lots and lots of prototypes and iterating on ideas

All of these are "trivial" once you have the main code, but they are incredibly valuable, and LLMs do a fantastic job.

replies(1): >>43660553 #
2. zahlman ◴[12 Apr 25 01:37 UTC] No.43660553[source]▶
I was referring specifically to boilerplate within the code itself. But sure, I can imagine some uses.