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

301–310 of 464 posts

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

#301

Post by viraptor »

viraptor wrote: post #85
stray wrote: post #38

Earlier quoted context omitted.

You're going to spend a little over $1k to ramp up your skills with AI-aided coding. It's dirt cheap in the grand scheme of things.

Not even close. I'm still under $100, creating full apps. Stick to reasonable models and you can achieve and learn a lot. You don't need latest and greatest in max mode (or whatever the new one calls it) for majority of the tasks. You can have to throw the whole project at the service every time either.

Typo: ...you don't have to throw the whole project context...

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

#302

Post by esailija »

adastra22 wrote: post #167
danieltanfh95 wrote: post #52

AI models are fundamentally trained on patterns from existing data - they learn to recognize and reproduce successful solution templates rather than derive solutions from foundational principles. When faced with a problem, the model searches for the closest match in its training experience rather than building up from basic assumptions and logical steps. Human experts excel at first-principles thinking precisely beca…

So are people. People are trained on existing data and learn to reproduce known solutions. They also take this to the meta level—a scientist or engineer is trained on methods for approaching new problems which have yielded success in the past. AI does this too. I’m not sure there is actually a distinction here..

There is a difference between extrapolating from just a few examples vs interpolating between trillion examples

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

#303

Post by planb »

nobunaga wrote: post #260
olmo23 wrote: post #250

Earlier quoted context omitted.

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.

ITT: People who think LLMs are AGI and can produce output that the LLM has come up with out of thin air or by doing research. Go speak with someone who is actually an expert in this field how LLMs work and why the training data is so important. Im amazed that people in the CS industry seem to talk like they know everything about a tech after using it but never even writing a line of code for an LLM. Our indsutry is d…

I think the time has come to not mean LLMs when talking about AI. An agent with web access can do so much more and hallucinates way less than "just" the model. We should start seeing the model as a building block of an AI system.

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

#305

Post by resource_waste »

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.

I have it write algorithms, explain why my code isnt working, write API calls, or make specific functions.

The entire code? Not there, but with debuggers, I've even started doing that a bit.

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

#307

Post by Philpax »

dotancohen wrote: post #271
Philpax wrote: post #225

Earlier quoted context omitted.

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.

> Those tasks can take hours, or at least long enough where multiple tasks are running in the background?

Maybe not hours, but extended periods of time, yes. Agents are very quick, so they can frequently complete tasks that would have taken me hours in minutes.

> The page says $17 per month. That's unlimited usage?

Each plan has a limited quota; the Pro plan offers you enough to get in and try out Claude Code, but not enough for serious use. The $100 and $200 plans still have quotas, but they're quite generous; people have been able to get orders of magnitude of API-cost-equivalents out of them [0].

> 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.

Perhaps, but for now, you still need to have some degree of vague competence to know what to look out for and what works best. Might I suggest using the tools to get work done faster so that you can relax for the rest of the day? ;)

[0]: https://xcancel.com/HaasOnSaaS/status/1932713637371916341

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

#308

Post by nottorp »

jasode wrote: post #235
nottorp wrote: post #222

Earlier quoted context omitted.

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.

>You remember when Google used to do the same thing for you way before "AI"? [...] stack trace [...], but a plain search used to be capable of giving the same answer as a LLM. The "plain" Google Search before LLM never had the capability to copy&paste an entire lengthy stack trace (e.g. ~60 frames of verbose text) because long strings like that exceeds Google's UI. Various answers say limit of 32 words and 5784 chara…

That's a good point, because now that I think of it, I never pasted a full stack trace in a search engine. I selected what looked to be the relevant part and pasted that.

But I did it subconsciously. I never thought of it until today.

Another skill that LLM use can kill? :)

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

#309

Post by skydhash »

dvt wrote: post #64

I'm actually quite bearish on AI in the generative space, but even I have to admit that writing boilerplate is "N" times faster using AI (use your favorite N). I hate when people claim this without any proof, so literally today this is what I asked ChatGPT: write a stub for a react context based on this section (which will function as a modal): ``` // a bunch of stuff ``` Worked great, it created a few files (the hoo…

For this case, i will probably lift off the example from the library docs. Or spend 5 minutes writing a bare implementation as it would be all I need at the time.

That’s an issue I have with generated code. More often, I start with a basic design that evolves based on the project needs. It’s an iterative process that can span the whole timeline. But with generated code, it’s a whole solution that fits the current needs, but it’s a pain to refactor.

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

#310

Post by Tzt »

mentalgear wrote: post #304

From all my experience over several years, the best stance towards AI assisted development is: "Trust, but verify" (each change). Which is in stark contrast of brittle "vibe coding" (which might work for demos but nothing else).

What do you mean several years, it became feasible like 6 months ago lol. No, gpt3.5 doesn't count, it's a completely useless thing.
Post reply on HN