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

381–390 of 464 posts

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

#381

Post by SpaceNugget »

ken47 wrote: post #10
frankc wrote: post #8

I just don't agree with this. I am generally telling the model how to do the work according to an architecture I specify using technology I understand. The hardest part for me in reviewing someone else's code is understanding their overall solution and how everything fits together as it's not likely to be exactly the way I would have structured the code or solved the problem. However, with an LLM it generally isn't s…

You can pre-agree on a solution path with human engineers too, with a similar effect.

I think the point of the comment you replied to is that "reviewing code" is different in a regular work situation of reviewing a coworkers PR vs checking that the LLM generated something that matches what you requested.

I don't send my coworkers lists of micromanaged directions that give me a pretty clear expectation of what their PR is going to look like. I do however, occasionally get tagged on a review for some feature I had no part in designing, in a part of some code base I have almost no experience with.

Reviewing that the components you asked for do what you asked is a much easier scenario.

Maybe if people are asking an LLM to build an entire product from scratch with no guidance it would take a lot more effort to read and understand the output. But I don't think most people do that on a daily basis.

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

#382

Post by NoGravitas »

mellosouls wrote: post #364

The author makes the excellent point that LLM-coding still has a human bottleneck at the code review point - regardless of whether the issue at hand is fixed or not. Leaving aside the fact that this isn't an LLM problem; we've always had tech debt due to cowboy devs and weak management or "commercial imperatives": I'd be interested to know if any of the existing LLM ELO style leaderboards mark for code quality in add…

> Leaving aside the fact that this isn't an LLM problem; we've always had tech debt due to cowboy devs and weak management or "commercial imperatives":

But this is one of the core problems with LLM coding, right? It accelerates an already broken model of software development (worse is better) rather than trying to help fix it.

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

#383

Post by marssaxman »

Jonovono wrote: post #99
marssaxman wrote: post #86

So far as I can tell, generative AI coding tools make the easy part of the job go faster, without helping with the hard part of the job - in fact, possibly making it harder. Coding just doesn't take that much time, and I don't need help doing it. You could make my coding output 100x faster without materially changing my overall productivity, so I simply don't bother to optimize there.

Are you a plumber perhaps?

Not if I can help it, no; I don't have the patience.

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

#385

Post by efavdb »

Workaccount2 wrote: post #365
b112 wrote: post #238

Earlier quoted context omitted.

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…

>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. How would you reconcile this with the fact that SOTA models are only a few TB in size? Trained on exabytes of data, yet only a few TB in the end. Correct answers couldn't be dumb luck either, because otherwise the models would…

Could it be that there is a lot of redundancy in the training data?

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

#386

Post by AlwaysRock »

plasticeagle wrote: post #206
socalgal2 wrote: post #180

> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense. I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search wo…

ChatGPT and Gemini literally only know the answer because they read StackOverflow. Stack Overflow only exists because they have visitors. What do you think will happen when everyone is using the AI tools to answer their questions? We'll be back in the world of Encyclopedias, in which central authorities spent large amounts of money manually collecting information and publishing it. And then they spent a good amount o…

> ChatGPT and Gemini literally only know the answer because they read StackOverflow. Stack Overflow only exists because they have visitors.

I mean... They also can read actual documentation. If I'm working on any api work or a language I'm not familiar with, I ask the LLM to include the source they got their answer from and use official documentation when possible.

That lowers the hallucination rate significantly and also lets me ensure said function or code actually does what the llm reports it does.

In theory, all stackoverflow answers are just regurgitated documentation, no?

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

#387

Post by Eisenstein »

perrygeo wrote: post #379
socalgal2 wrote: post #180

> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense. I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search wo…

> Getting answers to those question is learning, regardless of where the answer comes from. Sort of. The process of working through the question is what drives learning. If you just receive the answer with zero effort, you are explicitly bypassing the brain's learning mechanism. There's huge difference between your workflow and fully Agentic AIs though. Asking an AI for the answer in the way you describe isn't exactl…

The logical conclusion of this is 'the AI just solves the problem by coding without telling you about it'. If we think about 'what happens when everyone vibe-codes to solve their problems' then we get to 'the AI solves the problem for you, and you don't even see the code'.

Vibe-coding is just a stop on the road to a more useful AI and we shouldn't think of it as programming.

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

#388

Post by jrm4 »

thedelanyo wrote: post #195
socalgal2 wrote: post #180

> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense. I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search wo…

So AI is basically best as a search engine.

As I've said a bunch.

AI is a search engine that can also remix its results, often to good effect.

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

#389

Post by AstroBen »

lexandstuff wrote: post #54

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 solv…

> not having to expend brain energy to solve problems, and they're mistaking that for productivity

Couldn't this result in being able to work longer for less energy, though? With really hard mentally challenging tasks I find I cap out at around 3-4 hours a day currently

Like imagine if you could walk at running speed. You're not going faster.. but you can do it for way longer so your output goes up if you want it to

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

#390

Post by scotty79 »

> 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.

Even if that was true for everybody reviews would still be worth doing because when the code is reviewed it gets more than one pair of eyes looking at it.

So it's still worth using AI even if it's slower than writing code yourself. Because you wouldn't have made mistakes that AI would made and AI wouldn't make mistakes you would have made.

It still might be personally not worth it for you though if you prefer to write code than to read it. Until you can set up AI as a reviewer for yourself.

Post reply on HN