←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: 0.372s | source
Show context
gngoo ◴[20 Jul 25 09:24 UTC] No.44623319[source]▶
To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic).

The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as they did before. But the majority of devs who won’t even believe that it’s remotely possible to do so is also not helping this style of building/programming mature.

I wouldn’t even call it vibe coding anymore. I think the term hurts what it actually is. For me it’s just a huge force multiplier, maybe 10-20x of my ability to deliver with my own knowledge and skills on a web dev basis.

replies(7): >>44623365 #>>44623389 #>>44623432 #>>44623746 #>>44624942 #>>44625275 #>>44625458 #
dustingetz ◴[20 Jul 25 09:39 UTC] No.44623389[source]▶
your problem domain is greenfield freelancing if i am reading you correctly?

The tarpit of AI discussion is that everybody assumes that their local perspective is globally applicable. It is not.

replies(2): >>44623818 #>>44741390 #
1. Xss3 ◴[20 Jul 25 10:45 UTC] No.44623818[source]▶
This.

I work in a large corpo eco system of products across languages that talk to a mess of micro and not so micro services.

Ai tools are rarely useful out of the box in this context. Mostly because they can't fit the ecosystem into their context. I think i would need 10 agents or more for the task.

We have good documentation, but just fitting the documentation into context alongside a microservice is a tight fit. Most services would need one agent for the code (and even then it'd only fit 10% in context), and one for the docs.

Trying to use them without sufficient context, or trying to cram the right 10% into context, takes more effort than just coding the feature, and produces worse results with the worst kind of bugs, subtle ones borne from incorrect assumptions.