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

401–410 of 464 posts

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

#401

Post by semiquaver »

skydhash wrote: post #313
jumploops wrote: post #273

Earlier quoted context omitted.

> 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 amazing thing about LLMs is that we still don’t know how (or why) they work! You may want to take a course in machine learning and read a few papers.

Parent is right. We know mechanically how LLMs are trained and used but why they work as well as they do is very much not known.

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

#403

Post by semiquaver »

nobunaga wrote: post #352
usef- wrote: post #269

Earlier quoted context omitted.

This isn't about being AGI or not, and it's not "out of thin air". Modern implementations of LLMs can "do research" by performing searches (whose results are fed into the context), or in many code editors/plugins, the editor will index the project codebase/docs and feed relevant parts into the context. My guess is they either were using the LLM from a code editor, or one of the many LLMs that do web searches automati…

Yeah, doing web searches could be called research but thats not what we are talking bout. Read the parent of the parent. Its about being able to answer questions thats not in its training data. People are talking about LLMs making scientific discoveries that humans haven't. A ridiculous take. Its not possible and with the current state of tech never will be. I know what LLMs are trained on. Thats not the topic of con…

> Its about being able to answer questions thats not in its training data.

This happens all the time via RAG. The model “knows” certain things via its weights, but it can also inject much more concrete post-training data into its context window via RAG (e.g. web searches for documentation), from which it can usefully answer questions about information that may be “not in its training data”.

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

#404

Post by bdamm »

satisfice wrote: post #29
bdamm wrote: post #11

No offense intended, but this is written by a guy who has the spare time to write the blog. I can only assume his problem space is pretty narrow. I'm not sure what his workflow is like, but personally I am interacting with so many different tools, in so many different environments, with so many unique problem sets, that being able to use AIs for error evaluation, and yes, for writing code, has indeed been a game chan…

You think he's not using the tools correctly. I think you aren't doing your job responsibly. You must think he isn't trying very hard. I think you are not trying very hard... That is the two sides of the argument. It could only be settled, in principle, if both sides were directly observing each other's work in real-time. But, I've tried that, too. 20 years ago in a debate between dedicated testers and a group of Agi…

I am absolutely responsible for my work. That's why I spend so much time reading the code that I and others on my team write, and it's why I spend so much time building enormous test systems, and pulling deeply on the work of others. Thousands and thousands of hours go into work that the customer will never see, because I am responsible.

People's lives are literally at stake. If my systems screw up, people can die.

And I will continue to use AI to help get through all that. It doesn't make me any less responsible for the result.

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

#405

Post by jyounker »

notnullorvoid wrote: post #120
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…

Is it a skill worth learning though? How much does the output quality improve? How transferable is it across models and tools of today, and of the future? From what I see of AI programming tools today, I highly doubt the skills developed are going to transfer to tools we'll see even a year from now.

Describing things in enough detail that someone else can implement them is a pretty important skill. Learning how to break up a large project into smaller tasks that you can then delegate to others is also a pretty important skill.

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

#406

Post by dspillett »

danielbln wrote: post #321
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…

> 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 ri…

If it gets to the point where I can't compete in the role with those using LLMs, I'll move on. I'm not happy with remote teams essentially being the only way of working these days (if you aren't working alone) anyway, and various other directions the industry has moved in (the shit-show that is client-side stack for instance!).

Maybe I'll retrain for lab work, I know a few people in the area, yeah I'd need a pay cut, but… Heck, I've got the mortgage paid, so I could take quite a cut and not be destitute, especially if I get sensible and keep my savings where they are and building instead of getting tempted to spend them! I don't think it'll get to that point for quite a few years though, and I might have been due to throw the towel in by that point anyway. It might be nice to reclaim tinkering as a hobby rather than a chore!

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

#407

Post by jyounker »

layer8 wrote: post #265
cbsmith wrote: post #182

Earlier quoted context omitted.

It seems counter intuitive that the reader would no longer have that authorial instinct due to lack of writing. Like, maybe they never had it, in which case, yes. But being exposed to a lot of different "writing opinions" tends to hone your own. Let's say you're right though, and you lose that authorial instinct. If you've got five different proposals/PRs from five different models, each one critiqued by the other fo…

I don’t find this convincing. People generally don’t learn how to write a good novel just by reading a lot of them.

On the other hand, people who write good novels tend to read a lot. Reading isn't sufficient, but intensive reading generally seems to be required.

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

#408

Post by mdavid626 »

AI offers many solutions and also brings many problems. Some people like to see only the good side and act, as if there would be no bad side.

One of the biggest problem I see with AI is, that it makes people used to NOT to think. It takes lots of time and energy to learn to program and design complex software. AI doesn’t solve this - humans to be able to supervise need to have these skills. But why would new programmers learn them? AI writes their code! It’s already hard to convince them otherwise. This only leads to bad things.

Technology without proper control and wisdom, destroys human things. We saw this many times already.

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

#409

Post by bigbuppo »

wiseowise wrote: post #142
bigbuppo wrote: post #94

Earlier quoted context omitted.

Don't try to argue with those using AI coding tools. They don't interact well with actual humans, which is why they've been relegated to talking to the computer. We'll eventually have them all working on some busy projects to help with "marketing" to keep them distracted while the decent programmers that can actually work in a team environment can get back to useful work free of the terrible programmers and marketing…

> that can actually work in a team environment can get back to useful work free of the terrible programmers Is that what you and your buddies talk about at two hour long coffee/smoke breaks while “terrible” programmers work?

I mostly just look at numbers every once in a while and try to keep them going in the right direction.

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

#410

Post by maujun »

mdavid626 wrote: post #408

AI offers many solutions and also brings many problems. Some people like to see only the good side and act, as if there would be no bad side. One of the biggest problem I see with AI is, that it makes people used to NOT to think. It takes lots of time and energy to learn to program and design complex software. AI doesn’t solve this - humans to be able to supervise need to have these skills. But why would new programm…

Agreed.

StackOverflow makes it easier not think and copy-paste. Autocomplete makes it easier to not think and make typos (Hopefully you have static typing). Package management makes it easier to not think and introduce heavy dependencies. C makes it easier to not think and forget to initialize variables. I make it easier to not think and read without considering evil (What if every word I say has evil intention and effect?)

Post reply on HN