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

321–330 of 464 posts

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

#321

Post by danielbln »

dspillett wrote: post #226
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…

> 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…

> I want to be a tinkerer, not a manager of tinkerers.

We all want many things, doesn't mean someone will pay you for it. You want to tinker? Great, awesome, more power to you, tinker on personal projects to your heart's content. However, if someone pays you to solve a problem, then it is our job to find the best, most efficient way to cleanly do it. Can LLMs do this on their own most of the time? I think not, not right now at least. The combination of skilled human and LLM? Most likely, yes.

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

#322

Post by chasd00 »

nottorp wrote: post #222
socalgal2 wrote: post #184

Earlier quoted context omitted.

To add, another experience I had. I was using an API I'm not that familiar with. My program was crashing. Looking at the stack trace I didn't see why. Maybe if I had many months experience with this API it would be obvious but it certainly wasn't to me. For fun I just copy and pasted the stack trace into Gemini. ~60 frames worth of C++. It immediately pointed out the likely cause given the API I was using. I fixed th…

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.

I don’t think search use to do everything LLMs do now but you have a very good point. Search has gotten much worse. I would say search is about the quality it was just before google launched. My general search needs are being met more and more by Claude, I use google only when I know very specific keywords because of seo spam and ads.

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

#323

Post by rootnod3 »

PeterStuer wrote: post #241
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 h…

I might be an outlier, but I much prefer reading the documentation myself. One of the reasons I love using FreeBSD and OpenBSD as daily drivers. The documentation is just so damn good. Is it a pain in the ass at the beginning? Maybe. But I require way less documentation lookups over time and do not have to rely on AI for that.

Don't get me wrong, I tried. But even when pasting the documentation in, the amount of times it just hallucinated parameters and arguments that were not even there were such a huge waste of time, I don't see the value in it.

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

#324

Post by kenjackson »

globnomulous wrote: post #189
kenjackson wrote: post #114

Earlier quoted context omitted.

I can read code much faster than I can write it. This might be the defining line for Gen AI - people who can read code faster will find it useful and those that write faster then they can read won’t use it.

> I can read code much faster than I can write it. I have known and worked with many, many engineers across a wide range of skill levels. Not a single one has ever said or implied this, and in not one case have I ever found it to be true, least of all in my own case. I don't think it's humanly possible to read and understand code faster than you can write and understand it to the same degree of depth. The brain just…

You definitely can. For example I know x86. I can read it and understand it quite well. But if you asked me to write even a basic program in it, it would take me a considerable amount of time.

The same goes with shell scripting.

But more importantly you don’t have to understand code to the same degree and depth. When I read code I understand what the code is doing and if it looks correct. I’m not going over other design decisions or implementation strategies (unless they’re obvious). If I did that then I’d agree. Id also stop doing code reviews and just write everything myself.

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

#325

Post by rainonmoon »

jumploops wrote: post #273
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. The amazing thing about LLMs is that we still don’t know how (or why) they work! Yes, they’re magic mirrors that regurgitate the corpus of human knowledge. But as it turns out, most human knowledge is already regurgitation (see: the patent system). Novelty is rare, and LLMs have an incredible ability to pattern match and…

> the corpus of human knowledge.

Goodness this is a dim view on the breadth of human knowledge.

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

#326

Post by cwoolfe »

I have found AI generated code to be overly verbose and complex. It usually generates 100 lines and I take a few of them and adapt them to what I want. The best cases I've found for using it are asking specific technical questions, helping me learn a new code language, having it generate ideas on how to solve a problem for brainstorming. It also does well with bounded algorithmic problems that are well specified i.e. write a function that takes inputs and produces outputs according to xyz. I've found it's usually sorely lacking in domain knowledge (i.e. it is not an expert on the iOS SDK APIs, not an expert in my industry, etc.)

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

#327

Post by chii »

suddenlybananas wrote: post #320
chii wrote: post #297

Earlier quoted context omitted.

is it more important for a chess engine to be able to think? Or is it able to win by brute force through searching a sufficient outcome? If the outcome is indistinguisable from using "thinking" as the process rather than brute force, why would the process matter regarding how the outcome was achieved?

maybe if programming were a well-defined game like chess, but it's not.

the grammar of a programming language is just as well defined. And the defined-ness of the "game" isn't required for my argument.

Your concept of thinking is the classic retoric - as soon as some "ai" manages to achieve something which previously wasn't capable, it's no longer AI and is just xyz process. It happened with chess engines, with alphago, and with LLMs. The implication being that human "thinking" is somehow unique and only the AI that replicate it can be considered to have "thinking".

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

#328

Post by mettamage »

cwoolfe wrote: post #326

I have found AI generated code to be overly verbose and complex. It usually generates 100 lines and I take a few of them and adapt them to what I want. The best cases I've found for using it are asking specific technical questions, helping me learn a new code language, having it generate ideas on how to solve a problem for brainstorming. It also does well with bounded algorithmic problems that are well specified i.e.…

My heuristic: the more you're solving a solved problem that is just tedious work and memory intensive take a crack at using AI. It will probably one shot your solution with minimal tweaks required.

The more you deviate from that, the more you have to step in.

But given that I constantly forget how to open a file in Python, I still have a use for it. It basically supplanted Stackoverflow.

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

#329

Post by gwhr »

socalgal2 wrote: post #230
plasticeagle wrote: post #206

Earlier quoted context omitted.

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 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.

What kind of API is it? Curious if it's a common problem that the AI was able to solve?

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

#330

Post by demosthanos »

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 wrong. I write toy languages and frameworks for fun. These are APIs that simply don't exist outside of my code base, and LLMs are consistently able to:

* Read the signatures of the functions.

* Use the code correctly.

* Answer questions about the behavior of the underlying API by consulting the code.

Of course they're just guessing if they go beyond what's in their context window, but don't underestimate context window!

Post reply on HN