Generative AI coding tools and agents do not work for me • Hacker News Board

Re: Generative AI coding tools and agents do not work for me

#51

Post by qinsig » Tue, Jun 17, 2025, 2:32 AM UTC

dingnuts wrote: post #31

waprin wrote: post #19

To some degree, traditional coding and AI coding are not the same thing, so it's not surprising that some people are better at one than the other. The author is basically saying that he's much better at coding than AI coding. But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher ski…

> You might prefer manual coding, but you might just be bad at AI coding and you might prefer it if you improved at it. ok but how much am I supposed to spend before I supposedly just "get good"? Because based on the free trials and the pocket change I've spent, I don't consider the ROI worth it.

Avoid using agents that can just blow through money (cline, roocode, claudecode with API key, etc).

Instead you can get comfortable prompting and managing context with aider.

Or you can use claude code with a pro subscription for a fair amount of usage.

I agree that seeing the tools just waste several dollars to just make a mess you need to discard is frustrating.

Re: Generative AI coding tools and agents do not work for me

#52

Post by danieltanfh95 » Tue, Jun 17, 2025, 2:34 AM UTC

AI models are fundamentally trained on patterns from existing data - they learn to recognize and reproduce successful solution templates rather than derive solutions from foundational principles. When faced with a problem, the model searches for the closest match in its training experience rather than building up from basic assumptions and logical steps.

Human experts excel at first-principles thinking precisely because they can strip away assumptions, identify core constraints, and reason forward from fundamental truths. They might recognize that a novel problem requires abandoning conventional approaches entirely. AI, by contrast, often gets anchored to what "looks similar" and applies familiar frameworks even when they're not optimal.

Even when explicitly prompted to use first-principles analysis, AI models can struggle because:

- They lack the intuitive understanding of when to discard prior assumptions

- They don't naturally distinguish between surface-level similarity and deep structural similarity

- They're optimized for confident responses based on pattern recognition rather than uncertain exploration from basics

This is particularly problematic in domains requiring genuine innovation or when dealing with edge cases where conventional wisdom doesn't apply.

Context poisoning, intended or not, is a real problem that humans are able to solve relatively easily while current SotA models struggle.

Re: Generative AI coding tools and agents do not work for me

#53

Post by xarope » Tue, Jun 17, 2025, 2:34 AM UTC

roxolotl wrote: post #22

> But interns learn and get better over time. The time that you spend reviewing code or providing feedback to an intern is not wasted, it is an investment in the future. The intern absorbs the knowledge you share and uses it for new tasks you assign to them later on. This is the piece that confuses me about the comparison to a junior or an intern. Humans learn about the business, the code, the history of the system.…

I think this is how certain LLMs end up with 14k worth of system prompts

Re: Generative AI coding tools and agents do not work for me

#54

Post by lexandstuff » Tue, Jun 17, 2025, 2:47 AM UTC

Great article. The other thing that you miss out on when you don't write the code yourself is that sense of your subconscious working for you. Writing code has a side benefit of developing a really strong mental model of a problem, that kinda gets embedded in your neurons and pays dividends down the track, when doing stuff like troubleshooting or deciding on how to integrate a new feature. You even find yourself solving problems in your sleep.

I haven't observed any software developers operating at even a slight multiplier from the pre-LLM days at the organisations I've worked at. I think people are getting addicted to not having to expend brain energy to solve problems, and they're mistaking that for productivity.

Re: Generative AI coding tools and agents do not work for me

#55

Post by p1dda » Tue, Jun 17, 2025, 2:49 AM UTC

It would be interesting to see which is faster/better in competitive coding, the human coder or the human using AI to assist in coding.

Re: Generative AI coding tools and agents do not work for me

#56

Post by hooverd » Tue, Jun 17, 2025, 2:49 AM UTC

strangescript wrote: post #47

kibibu wrote: post #25

Earlier quoted context omitted.

I have never seen people work harder to dismantle their own industry than software engineers are right now.

What exactly is the alternative? Wish it away? Developers have been automating away jobs for decades, its seems hypocritical to complain about it now.

who gets the spoils?

Re: Generative AI coding tools and agents do not work for me

#57

Post by hatefulmoron » Tue, Jun 17, 2025, 2:54 AM UTC

adriand wrote: post #28

jumploops wrote: post #2

> It takes me at least the same amount of time to review code not written by me than it would take me to write the code myself, if not more. As someone who uses Claude Code heavily, this is spot on. LLMs are great, but I find the more I cede control to them, the longer it takes to actually ship the code. I’ve found that the main benefit for me so far is the reduction of RSI symptoms, whereas the actual time savings a…

Do you have to review the code? I’ll be honest that, like the OP theorizes, I often just spot review it. But I also get it to write specs (often very good, in terms of the ones I’ve dug into), and I always carefully review and test the results. Because there is also plenty of non-AI code in my projects I didn’t review at all, namely, the myriad open source libraries I’ve installed.

It depends on what you're doing. If it's a simple task, or you're making something that won't grow into something larger, eyeballing the code and testing it is usually perfect. These types of tasks feel great with Claude Code.

If you're trying to build something larger, it's not good enough. Even with careful planning and spec building, Claude Code will still paint you into a corner when it comes to architecture. In my experience, it requires a lot of guidance to write code that can be built upon later.

The difference between the AI code and the open source libraries in this case is that you don't expect to be responsible for the third-party code later. Whether you or Claude ends up working on your code later, you'll need it to be in good shape. So, it's important to give Claude good guidance to build something that can be worked on later.

Re: Generative AI coding tools and agents do not work for me

#58

Post by stray » Tue, Jun 17, 2025, 2:55 AM UTC

ken47 wrote: post #18

bdamm wrote: post #11

No offense intended, but this is written by a guy who has the spare time to write the blog. I can only assume his problem space is pretty narrow. I'm not sure what his workflow is like, but personally I am interacting with so many different tools, in so many different environments, with so many unique problem sets, that being able to use AIs for error evaluation, and yes, for writing code, has indeed been a game chan…

> rise of IDEs, or Google search, or AWS. None of these things introduced the risk of directly breaking your codebase without very close oversight. If LLMs can surpass that hurdle, then we’ll all be having a different conversation.

A human deftly wielding an LLM can surpass that hurdle. I laugh at the idea of telling Claude Code to do the needful and then blindly pushing to prod.

Re: Generative AI coding tools and agents do not work for me

#59

Post by sponnath » Tue, Jun 17, 2025, 3:04 AM UTC

strangescript wrote: post #9

Everyone is still thinking about this problem the wrong way. If you are still running one agent, on one project at a time, yes, its not going to be all that helpful if you are already a fast, solid coder. Run three, run five. Prompt with voice annotation. Run them when normally you need a cognitive break. Run them while you watch netflix on another screen. Have them do TDD. Use an orchestrator. So many more options.…

Can you actually demonstrate this workflow producing good software?

Re: Generative AI coding tools and agents do not work for me

#60

Post by __MatrixMan__ » Tue, Jun 17, 2025, 3:04 AM UTC

skydhash wrote: post #35

waprin wrote: post #19

To some degree, traditional coding and AI coding are not the same thing, so it's not surprising that some people are better at one than the other. The author is basically saying that he's much better at coding than AI coding. But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher ski…

> But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher skill ceiling than many people realize No, it's not. It's something you can pick in a few minutes (or an hour if you're using more advanced tooling, mostly spending it setting things up). But it's not like GDB or using UNIX as…

It definitely takes more than minutes to discover the ways that your model is going to repeatedly piss you off and set up guardrails to mitigate those problems.