Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Generative AI coding tools and agents do not work for me

blog.miguelgrinberg.com

Post reply on HN
Print view View original

281–290 of 464 posts

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

#281

Post by layer8 »

afarviral wrote: post #122

This has been my experience as well, but there are plenty of assertions here that are not always true, e.g. "AI coding tools are sophisticated enough (they are not) to fix issues in my projects" … but how do you know this if you are not constantly checking whether the tooling has improved? I think for a certain level of issue AI can tackle it and improve things, but there's only a subset of the available models and o…

You omitted “with little or no supervision”, which I think is crucial to that quote. It’s pretty undisputed that having an AI fix issues in your code requires some amount of supervision that isn’t negligible. I.e. you have to review the fixes, and possibly make some adjustments.

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

#282

Post by averageRoyalty »

rwmj wrote: post #277
dspillett wrote: post #226

Earlier quoted context omitted.

> To some degree, traditional coding and AI coding are not the same thing LLM-based¹ coding, at least beyond simple auto-complete enhancements (using it directly & interactively as what it is: Glorified Predictive Text) is more akin to managing a junior or outsourcing your work. You give a definition/prompt, some work is done, you refine the prompt and repeat (or fix any issues yourself), much like you would with an…

Another difference if your junior will, over time, learn, and you'll also get a sense of whether you can trust them. If after a while they aren't learning and you can't trust them, you get rid of them. GenAI doesn't gain knowledge in the same way, and you're always going to have the same level of trust in it (which in my experience is limited). Also if my junior argued back and was wrong repeatedly, that's be bad. Lu…

Cline, Roocode etc have the concept of rules that can be added to over time. There are heaps of memory bank and orchestration methods for AI.

LLMs absolutely can improve over time.

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

#284

Post by redhale »

This line by the author, in response to one of the comments, betrays the core of the article imo:

> The quality of the code these tools produce is not the problem.

So even if an AI could produce code of a quality equal to or surpassing the author's own code quality, they would still be uninterested in using it.

To each their own, but it's hard for me to accept an argument that such an AI would provide no benefit, even if one put priority on maintaining high quality standards. I take the point that the human author is ultimately responsible, but still.

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

#287

Post by hombre_fatal »

b112 wrote: post #238
socalgal2 wrote: post #230

Earlier quoted context omitted.

> ChatGPT and Gemini literally only know the answer because they read StackOverflow. Stack Overflow only exists because they have visitors. I know this isn't true because I work on an API that has no answers on stackoverflow (too new), nor does it have answers anywhere else. Yet, the AI seems to able to accurately answer many questions about it. To be honest I've been somewhat shocked at this.

It is absolutely true, and AI cannot think, reason, comprehend anything it has not seen before. If you're getting answers, it has seen it elsewhere, or it is literally dumb, statistical luck. That doesn't mean it knows the answer . That means it guessed or hallucinated correctly. Guessing isn't knowing. edit: people seem to be missing my point, so let me rephrase. Of course AIs don't think, but that wasn't what I was…

This doesn't seem like a useful nor accurate way of describing LLMs.

When I built my own programming language and used it to build a unique toy reactivity system and then asked the LLM "what can I improve in this file", you're essentially saying it "only" could help me because it learned how it could improve arbitrary code before in other languages and then it generalized those patterns to help me with novel code and my novel reactivity system.

"It just saw that before on Stack Overflow" is a bad trivialization of that.

It saw what on Stack Overflow? Concrete code examples that it generalized into abstract concepts it could apply to novel applications? Because that's the whole damn point.

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

#288

Post by ukprogrammer »

> “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.”

There’s your issue, the skill of programming has changed.

Typing gets fast; so does review once robust tests already prove X, Y, Z correctness properties.

With the invariants green, you get faster at grokking the diff, feed style nits back into the system prompt, and keep tuning the infinite tap to your taste.

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

#289

Post by nottorp »

nsonha wrote: post #276
nottorp wrote: post #222

Earlier quoted context omitted.

You remember when Google used to do the same thing for you way before "AI"? Okay, maybe sometimes the post about the stack trace was in Chinese, but a plain search used to be capable of giving the same answer as a LLM. It's not that LLMs are better, it's search that got entshittified.

> when Google used to do the same thing for you way before "AI"? Which is never? Do you often just lie to win arguments? LLM gives you a synthesized answer, search engine only returns what already exists. By definition it can not give you anything that is not a super obvious match

> Which is never?

In my experience it was "a lot". Because my stack traces were mostly hardware related problems on arm linux in that period.

But I suppose your stack traces were much different and superior and no one can have stack traces that are different from yours. The world is composed of just you and your project.

> Do you often just lie to win arguments?

I do not enjoy being accused of lying by someone stuck in their own bubble.

When you said "Which is never" did you lie consciously or subconsciously btw?

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

#290

Post by ukprogrammer »

jdbernard wrote: post #30
adventured wrote: post #17

Earlier quoted context omitted.

The conversations will climb the ladder and narrow. Eventually: well, but, the AI coding agent isn't better than a top 10%/5%/1% software developer. And it'll be that the coding agents can't do narrow X thing better than a top tier specialist at that thing. The skeptics will forever move the goal posts.

If the AI actually outperforms humans in the full context of the work, then no, we won't. It will be so much cheaper and faster that businesses won't have to argue at all. Those that adopt them will massively outcompetes those that don't. However, assuming we are still having this conversation, that alone is proof to me that the AI is not that capable. We're several years into "replace all devs in six months." We wil…

> If the AI actually outperforms humans in the full context of the work, then no, we won't. It will be so much cheaper and faster that businesses won't have to argue at all. Those that adopt them will massively outcompetes those that don't.

This. The dev's outcompeting by using AI today are too busy shipping, rather than wasting time writing blog posts about what ultimately, is a skill-issue.

Post reply on HN