Live data from Hacker News

AI makes the easy part easier and the hard part harder

blundergoat.com

21–30 of 382 posts

Re: AI makes the easy part easier and the hard part harder

#21
post #5

[flagged]

> It's so intriguing, I wonder if the people who are against it haven't even used it properly. I feel like this is a common refrain that sets an impossible bar for detractors to clear. You can simply hand wave away any critique with “you’re just not using it right.” If countless people are “using it wrong” then maybe there’s something wrong with the tool.

A bunch of people with no construction experience could collectively get together and start complaining that their ball pein hammers aren't working.

Doesn't mean the hammers are bad, no matter how many people join the community.

You need to learn how to use the tools.

Re: AI makes the easy part easier and the hard part harder

#22
post #5

[flagged]

What we call AI at the heart of coding agents, is the averaged “echo” of what people have published on the web that has (often illegitimately) ended up in training data. Yes it probably can spit out some trivial snippets but nothing near what’s needed for genuine software engineering.

Also, now that StackOverflow is no longer a thing, good luck meaningfully improving those code agents.

Re: AI makes the easy part easier and the hard part harder

#24
post #9

I vibe coded a retro emulator and assembler with tests. Prompts were minimal and I got really great results (Gemini 3). I tried vibe coding the tricky proprietary part of an app I worked on a few years ago; highly technical domain (yes vague don’t care to dox myself). Lots of prompting and didn’t get close. There are literally thousands of retro emulators on github. What I was trying to do had zero examples on GitHub…

I call these "embarrassingly solved problems". There are plenty of examples of emulators on GitHub, therefore emulators exist in the latent spaces of LLMs. You can have them spit one out whenever you want. It's embarrassingly solved.

There are no examples of what you tried to do.

Re: AI makes the easy part easier and the hard part harder

#25

Earlier quoted context omitted.

> It's so intriguing, I wonder if the people who are against it haven't even used it properly. I feel like this is a common refrain that sets an impossible bar for detractors to clear. You can simply hand wave away any critique with “you’re just not using it right.” If countless people are “using it wrong” then maybe there’s something wrong with the tool.

A bunch of people with no construction experience could collectively get together and start complaining that their ball pein hammers aren't working. Doesn't mean the hammers are bad, no matter how many people join the community. You need to learn how to use the tools.

A bunch of people with poor programming experience could get together and start claiming their new tool is the future.

Doesn’t mean the tool is actually useful, no matter how many people join the community.

Re: AI makes the easy part easier and the hard part harder

#27
I think AI is just a massive force multiplier. If your codebase has bad foundation and going in the wrong direction with lots of hacks, it will just write code which mirrors the existing style... And you get exactly was OP is suggesting.

If however, your code foundations are good and highly consistent and never allow hacks, then the AI will maintain that clean style and it becomes shockingly good; in this case, the prompting barely even matters. The code foundation is everything.

But I understand why a lot of people are still having a poor experience. Most codebases are bad. They work (within very rigid constraints, in very specific environments) but they're unmaintainable and very difficult to extend; require hacks on top of hacks. Each new feature essentially requires a minor or major refactoring; requiring more and more scattered code changes as everything is interdependent (tight coupling, low cohesion). Productivity just grinds to a slow crawl and you need 100 engineers to do what previously could have been done with just 1. This is not a new effect. It's just much more obvious now with AI.

I've been saying this for years but I think too few engineers had actually built complex projects on their own to understand this effect. There's a parallel with building architecture; you are constrained by the foundation of the building. If you designed the foundation for a regular single storey house, you can't change your mind half-way through the construction process to build a 20-storey skyscraper. That said, if your foundation is good enough to support a 100 storey skyscraper, then you can build almost anything you want on top.

My perspective is if you want to empower people to vibe code, you need to give them really strong foundations to work on top of. There will still be limitations but they'll be able to go much further.

My experience is; the more planning and intelligence goes into the foundation, the less intelligence and planning is required for the actual construction.

Re: AI makes the easy part easier and the hard part harder

#28
post #5

[flagged]

I've seen some discussions and I'd say there's lots of people who are really against the hyped expectations from the AI marketing materials, not necessarily against the AI itself. Things that people are against that would seem to be against AI, but are not directly against AI itself:

- Being forced to use AI at work

- Being told you need to be 2x, 5x or 10x more efficient now

- Seeing your coworkers fired

- Seeing hiring freeze because business think no more devs are needed

- Seeing business people make a mock UI with AI and boasting how programming is easy

- Seeing those people ask you to deliver in impossible timelines

- Frontend people hearing from backend how their job is useless now

- Backend people hearing from ML Engineers how their job is useless now

- etc

When I dig a bit about this "anti-AI" trend I find it's one of those and not actually against the AI itself.

Re: AI makes the easy part easier and the hard part harder

#29

Earlier quoted context omitted.

A bunch of people with no construction experience could collectively get together and start complaining that their ball pein hammers aren't working. Doesn't mean the hammers are bad, no matter how many people join the community. You need to learn how to use the tools.

A bunch of people with poor programming experience could get together and start claiming their new tool is the future. Doesn’t mean the tool is actually useful, no matter how many people join the community.

Except my analogy is correct and yours is clearly biased. Continue to not use the tools and become irrelevant.
Post reply on HN