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

271–280 of 464 posts

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

#271

Post by dotancohen »

Philpax wrote: post #225
dotancohen wrote: post #199

Earlier quoted context omitted.

> a couple Claude instances running in the background chewing through simple yet time consuming tasks. If you don't mind, I'd love to hear more about this. How exactly are they running the background? What are they doing? How do you interact with them? Do they have access to your file system? Thank you!

I would guess that they're running multiple instances of Claude Code [0] in the background. You can give it arbitrary tasks up to a complexity ceiling that you have to figure out for yourself. It's a CLI agent, so you can just give it directives in the relevant terminal. Yes, they have access to the filesystem, but only what you give them. [0]: https://www.anthropic.com/claude-code

Those tasks can take hours, or at least long enough where multiple tasks are running in the background? The page says $17 per month. That's unlimited usage?

If so, it does seem that AI just replaced me at my job... don't let them know. A significant portion of my projects are writing small business tools.

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

#272

Post by Vinnl »

didibus wrote: post #136
wiseowise wrote: post #131

Earlier quoted context omitted.

You’re twisting results. Just because they took more time doesn’t mean their productivity went down. On the contrary, if you can perform expert task with much less mental resources (which 99% of orgs should prioritize for) then it is an absolute win. Work is extremely mentally draining and soul crushing experience for majority of people, if AI can lower that while maintaining roughly same result with subjects allocat…

If I follow what you are saying, employers won't see any benefits, but employees, while they will take the same time and create the same output in the same amount of time, will be able to do so at a reduced mental strain? Personally, I don't know if this is always a win, mostly because I enjoy the creative and problem solving aspect of coding, and reducing that to something that is more about prompting, correcting, a…

Steelmanning their argument, employers will see benefits because while the employee might be more productive than with an LLM in the first two hours of the day, the cognitive load reduces their productivity as the day goes on. If employees are able to function at a higher level for longer during their day with an LLM, that should benefit the employer.

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

#273

Post by jumploops »

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 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 see issues in “novel” code, because they’ve seen those same patterns elsewhere.

Do they hallucinate? Absolutely.

Does that mean they’re useless? Or does that mean some bespoke code doesn’t provide the most obvious interface?

Having dealt with humans, the confidence problem isn’t unique to LLMs…

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

#274

Post by layer8 »

didibus wrote: post #132

You could argue that AI-generated code is a black box, but let's adjust our perspective here. When was the last time you thoroughly reviewed the source code of a library you imported? We already work with black boxes daily as we evaluate libraries by their interfaces and behaviors, not by reading every line. The distinction isn't whether code comes from AI or humans, but how we integrate and take responsibility for i…

Would you use a library that was written by AI without anyone having supervised it and thoroughly reviewed the code? We are using libraries without checking its source code because of the human thought process and quality control that has gone into it, and existing reputation. Nobody would use a library that no one else has ever seen and whose source code no human has ever laid their eyes on. (Excluding code generated by deterministic vetted tools here, like transpilers or parser generators.)

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

#275

Post by rwmj »

> What I think happens is that these people save time because they only spot review the AI generated code, or skip the review phase altogether, which as I said above would be a deal breaker for me.

In my experience it's that they dump the code into a pull request and expect me to review it. So GenAI is great if someone else is doing the real work.

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

#276

Post by nsonha »

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.

> 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

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

#277

Post by rwmj »

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…

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. Lucky that has never happened with AIs ...

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

#278

Post by chii »

suddenlybananas wrote: post #193
dr_dshiv wrote: post #192

Earlier quoted context omitted.

It’s mostly attitude that you are learning. Playfulness, persistence and a willingness to start from scratch again and again.

>persistence and a willingness to start from scratch again and again. i.e. continually gambling and praying the model spits something out that works instead of thinking.

why is the process important? If they can continuously trial and error their way into a good output/result, then it's a fine outcome.

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

#279

Post by zacksiri »

LLMs are relatively new technology. I think it's important to recognize the tool for what it is and how it works for you. Everyone is going to get different usage from these tools.

What I personally find is. It's great for helping me solve mundane things. For example I'm recently working on an agentic system and I'm using LLMs to help me generate elasticsearch mappings.

There is no part of me that enjoy making json mappings, it's not fun nor does it engage my curiosity as a programmer, I'm also not going to learn much from generating elasticsearch mappings over and over again. For problems like this, I'm happy to just let the LLM do the job. I throw some json at it and I've got a prompt that's good enough that it will spit out results deterministically and reliably.

However if I'm exploring / coding something new, I may try letting the LLM generate something. Most of the time though in these cases I end up hitting 'Reject All' after I've seen what the LLM produces, then I go about it in my own way, because I can do better.

It all really depends on what the problem you are trying to solve. I think for mundane tasks LLMs are just wonderful and helps get out of the way.

If I put myself into the shoes of a beginner programmer LLMs are amazing. There is so much I could learn from them. Ultimately what I find is LLMs will help lower the barrier of entry to programming but does not mitigate the need to learn to read / understand / reason about the code. Beginners will be able to go much further on their own before seeking out help.

If you are more experienced you will probably also get some benefits but ultimately you'd probably want to do it your own way since there is no way LLMs will replace experienced programmer (not yet anyway).

I don't think it's wise to completely dismiss LLMs in your workflow, at the same time I would not rely on it 100% either, any code generated needs to be reviewed and understood like the post mentioned.

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

#280

Post by averageRoyalty »

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.

A horse used to get you places just like a car could. A wisk worked as well as a blender.

We have a habit of finding efficiencies in our processes, even if the original process did work.

Post reply on HN