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

241–250 of 464 posts

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

#241

Post by PeterStuer »

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…

I love leaning new things. With ai I am learning more and faster.

I used to be on the Microsoft stack for decades. Windows, Hyper-V, .NET, SQL Server ... .

Got tired of MS's licensing BS and I made the switch.

This meant learning Proxmox, Linux, Pangolin, UV, Python, JS, Bootstrap, NGinx, Plausible, SQLite, Postgress ...

Not all of these were completely new, but I had never dove in seriously.

Without AI, this would have been a long and daunting project. AI made this so much smoother. It never tires of my very basic questions.

It does not always answer 100% correct the first time (tip: paste in the docs of specific version of the thing you are trying to figure out as it sometimes has out-of-date or mixed version knowledge), but most often can be nudged and prodded to a very helpfull result.

AI is just an undeniably superior teacher than Google or Stack Overflow ever was. You still do the learning, but the AI is great in getting you to learn.

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

#242

Post by greybox »

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…

I trust chatgpt and gemini a lot less than stackoverflow. On stackoverflow I can see the context that the answer to the original question was given in. AI does not do this. I've asked chatgpt questions about cmake for instance that it got subtly wrong, if I had not noticed this it would have cost me aa lot of time.

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

#243

Post by nottorp »

addandsubtract wrote: post #232
nottorp wrote: post #223

Earlier quoted context omitted.

But it does give you a ready to copy paste answer instead of a 'teach the man how to fish' answer.

Not if you prompt it to explain the answer it gives you.

Not the same thing. Copying code, even with comprehensive explanations, teaches less than writing/adjusting your own code based on advice.

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

#244

Post by smaudet »

vidarh wrote: post #213
smaudet wrote: post #140

Earlier quoted context omitted.

> We get in trouble trying to be clever (or DRY) Certainly, however: > That's the point I'm making about reviewing LLM code: you are not on the hook for making it work The second portion of your statement is either confusing (something unsaid) or untrue (you are still ultimately on the hook). Agentic AI is just yet another, as you put it way to "get in trouble trying to be clever". My previous point stands - if it wa…

> The second portion of your statement is either confusing (something unsaid) or untrue (you are still ultimately on the hook). You're missing the point. tptacek is saying he isn't the one who needs to fix the issue because he can just reject the PR and either have the AI agent refine it or start over. Or ultimately resort to writing the code himself. He doesn't need to make the AI written code work , and so he doesn…

> But no template based generator could write that code, even though it's fairly trivial

Not true at all, in fact this sort of thing used to happen all the time 10 years ago, code reading APIs and generating clients...

> He doesn't need to make the AI written code work, and so he doesn't need to spend a lot of time reading the AI written code - he can skim it for any sign it looks even faintly off and just kill it if that's the case instead of spending more time on it.

I think you are missing the point as well, that's still review, that's still being on the hook.

Words like "skim" and "kill" are the problem here, not a solution. They point to a broken process that looks like its working...until it doesn't.

But I hear you say "all software works like that", well, yes, to some degree. The difference being, one you hopefully actually wrote and have some idea what's going wrong, the other one?

Well, you just have to sort of hope it works and when it doesn't, well you said it yourself. Your code was garbage anyways, time to "kill" it and generate some new slop...

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

#245

Post by lechatonnoir »

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 is such a pointless, tired take.

You want to say this guy's experience isn't reproducible? That's one thing, but that's probably not the case unless you're assuming they're pretty stupid themselves.

You want to say that it Is reproducible, but that "that doesn't mean AI can think"? Okay, but that's not what the thread was about.

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

#246

Post by sensanaty »

tptacek wrote: post #106

I'm fine with anybody saying AI agents don't work for their work-style and am not looking to rebut this piece, but I'm going to take this opportunity to call something out. The author writes "reviewing code is actually harder than most people think. 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". That sounds within an SD of true for me, to…

But how is this a more efficient way of working? What if you have to have it open 30 PRs before 1 of them is acceptable enough to not outright ignore? It sounds absolutely miserable, I'd rather review my human colleague's work because in 95% of cases I can trust that it's not garbage.

The alternative where I boil a few small lakes + a few bucks in return for a PR that maybe sometimes hopefully kinda solves the ticket sounds miserable. I simply do not want to work like that, and it doesn't sound even close to efficient or speedier or anything like that, we're just creating extra work and extra waste for literally no reason other than vague marketing promises about efficiency.

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

#247

Post by freehorse »

nilirl wrote: post #237

The main claim made: When there's money or reputation to be lost, code requires the same amount of cognition; irrespective of who wrote the code, AI or not. Best counter claim: Not all code has the same risk. Some code is low risk, so the risk of error does not detract from the speed gained. For example, for proof of concepts or hobby code. The real problem: Disinformation. Needless extrapolation, poor analogies, ove…

> Best counter claim: Not all code has the same risk. Some code is low risk, so the risk of error does not detract from the speed gained. For example, for proof of concepts or hobby code.

Counter counter claim for these use cases: when I do proof of concept, I actually want to increase my understanding of said concept at the same time, learn challenges involved, and in general get a better idea how feasible things are. An AI can be useful for asking questions, asking for reviews, alternative solutions, inspiration etc (it may have something interesting to add or not) but if we are still in the territory "this matters" I would rather not substitute the actual learning experience and deeper understanding with having an AI generate code faster. Similar for hobby projects, do I need that thing to just work or I actually care to learn how it is done? If the learning/understanding is not important in a context, I would say then using AI to generate the code is a great time-saver. Otherwise, I may still use AI but not in the same way.

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

#248

Post by PeterStuer »

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…

What would convince you otherwise? The reason I ask is because you sound like you have made up your mind phylosophically, not based on practical experience.

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

#249

Post by rsanheim »

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…

It's just Pattern matching. Most APIs, and hell, most code is not unique or special. Its all been done a thousands of times before. Thats why an LLM can be helpful on some tool you've written just for yourself and never released anywhere.

As to 'knows the answer', I'm don't even know what that means with these tools. All I know is if it is helpful or not.

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

#250

Post by olmo23 »

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…

Where does the knowledge come from? People can only post to SO if they've read the code or the documentation. I don't see why LLMs couldn't do that.
Post reply on HN