←back to thread

Nobody knows how to build with AI yet

(worksonmymachine.substack.com)
526 points Stwerner | 9 comments | 19 Jul 25 15:45 UTC | HN request time: 0.411s | source | bottom
Show context
karel-3d ◴[19 Jul 25 16:32 UTC] No.44616917[source]▶
Reading articles like this feels like being in a different reality.

I don't work like this, I don't want to work like this and maybe most importantly I don't want to work with somebody who works like this.

Also I am scared that any library that I am using through the myriad of dependencies is written like this.

On the other hand... if I look at this as some alternate universe where I don't need to directly or indirectly touch any of this... I am happy that it works for these people? I guess? Just keep it away from me

replies(20): >>44617013 #>>44617014 #>>44617030 #>>44617053 #>>44617173 #>>44617207 #>>44617235 #>>44617244 #>>44617297 #>>44617336 #>>44617355 #>>44617366 #>>44617387 #>>44617482 #>>44617686 #>>44617879 #>>44617958 #>>44617997 #>>44618547 #>>44618568 #
lordnacho ◴[19 Jul 25 16:42 UTC] No.44617013[source]▶
But you also can't not swim with the tide. If you drove a horse-buggy 100 years ago, it was probably worth your while to keep your eye on whether motor-cars went anywhere.

I was super skeptical about a year ago. Copilot was making nice predictions, that was it. This agent stuff is truly impressive.

replies(7): >>44617059 #>>44617096 #>>44617165 #>>44617303 #>>44617421 #>>44617514 #>>44618157 #
mnky9800n ◴[19 Jul 25 16:50 UTC] No.44617096[source]▶
I think the agent stuff is impressive because we are giving the AI scaffold and tools and things to do. And that is why it is impressive because it has some directive. But it is obvious if you don't give it good directives it doesn't know what to do. So for me, I think a lot of jobs will be making agents do things, but a lot won't. i think its really strange that people are all so against all this stuff. it's cool new computer tools, does nobody actually like computers anymore?
replies(4): >>44617132 #>>44617159 #>>44617335 #>>44622092 #
1. prinny_ ◴[19 Jul 25 16:56 UTC] No.44617159[source]▶
A lot of people join this profession because they like building stuff. They enjoy thinking about a problem and coming up with a solution and then implementing and testing it. Prompting is not the same thing and it doesn't scratch the same itch and at the end of the day it's important to enjoy your job, not only be efficient at it.

I have heard the take that "writing code is not what makes you an engineer, solving problems and providing value is what makes you an engineer" and while that's cool and all and super important for advancing in your career and delivering results, I very much also like writing code. So there's that.

replies(6): >>44617289 #>>44617310 #>>44617354 #>>44617386 #>>44617536 #>>44618236 #
2. closewith ◴[19 Jul 25 17:11 UTC] No.44617289[source]▶
Most people don't enjoy their jobs and go to work for one reason only - to support themselves and their families. The itch is to get paid. This is as true in software as it is in other fields.

That's not to say there aren't vocations, or people in software who feel the way you do, but it's a tiny minority.

3. theferret ◴[19 Jul 25 17:12 UTC] No.44617310[source]▶
That's an interesting take - that you like the act of writing code. I think a lot of builders across a variety of areas feel this way. I like writing code too.

I've been experimenting with a toolchain in which I speak to text to agents, navigate the files with vim and autocomplete, and have Grok think through some math for me. It's pretty fun. I wonder if that will change to tuning agents to write code that go through that process in a semi-supervised manner will be fun? I don't know, but I'm open to the idea that as we progress I will find toolchains that bring me into flow as I build.

4. SoftTalker ◴[19 Jul 25 17:17 UTC] No.44617354[source]▶
Rick Beato posted a video recently where he created a fictitious artist and a couple of songs based on a few prompts. The results were somewhat passable, generic indie/pop music but as he said (I'm paraphrasing) "I didn't create anything here. I prompted a computer to put together a bunch of words and melodies that it knew from what other people had written."
5. johannes1234321 ◴[19 Jul 25 17:21 UTC] No.44617386[source]▶
There is code which is interesting to write, even if it isn't the area with clever algorithms or big architecture decisions or something.

But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion. Current AI systems widen that area.

The trouble with AI is when you are reaching the boundary of its capabilities. The trivial stuff it does well. For the complex stuff it fails spectacularly. In the in between you got to review carefully, which easily becomes less fun than simply writing by oneself.

replies(1): >>44618474 #
6. mnky9800n ◴[19 Jul 25 17:37 UTC] No.44617536[source]▶
Yeah but I write the code that is interesting to solve and let the LLM solve the problems that are not so important. Like making yet another webscraper tool is not the most exciting part of the process when you are trying to make some kind of real time inference tool for what people post on the internet.
7. fragmede ◴[19 Jul 25 18:48 UTC] No.44618236[source]▶
Ah yes, that "is that 6 spaces or 8" in a yaml file itch that just has to be scratched. Programming has a lot of doldrums. LLMs still get stuck at places, and that's just where the new itch to scratch is. Yeah, it's not the same as code golfing an algorithm really neatly into a few lines of really expressive C++, but things change and life goes on. Programming isn't the same as when it was on punch cards either.
8. ModernMech ◴[19 Jul 25 19:20 UTC] No.44618474[source]▶
> But there is also the area of boilerplate, where non-LLM-AI-based IDEs for a few decades already help a lot with templates and "smart" completion.

The thing for me is that AI writing the boilerplate feels like the brute force solution, compared to investing in better language and tooling design that may obviate the need for such boilerplate in the first place.

replies(1): >>44618594 #
9. johannes1234321 ◴[19 Jul 25 19:34 UTC] No.44618594{3}[source]▶
Yeah, but building tooling is a hard sell considering the ability of contemporary AI.

The energy cost is absurdly high for the result, but in current economics, where it's paid by investors not users, it's hidden. Will be interesting to see when AI companies got to the level where they have to make profits and how much optimisation there is to come ...