Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPTs and Feeling Left Behind

whynothugo.nl

Post reply on HN
Print view View original

81–90 of 226 posts

Re: GPTs and Feeling Left Behind

#81

Post by thrown-0825 »

jvanderbot wrote: post #44
martinald wrote: post #20

I'm completely equally lost the other way. I've went through multiple phases of LLM usage for development. GPT3.5 era: wow this is amazing, oh. everything is hallucinated. not actually as useful as I first thought GPT4 era: very helpful as stackoverflow on steroids. Claude 3.5 Sonnet: have it open pretty much all the time, constantly asking questions and getting it to generate simple code (in the web UI) when it goes…

I'm convinced the vast difference in outcome with LLM use is a product of the vast difference in jobs. For front end work it's just amazing. Spits out boilerplate and makes alterations without any need of help. For domain specific backend, for example robotics, it's bad. Tries to puke bespoke a-star, or invents libraries and functions. I'm way better off hand coding these things. The problem is this is classic Gell M…

If there is an abundance of medium / stack overflow articles it does well.

Re: GPTs and Feeling Left Behind

#82

Post by thrown-0825 »

hckrfucrs wrote: post #57
calrain wrote: post #42

Earlier quoted context omitted.

I get your position, and I don't want to sound dismissive, but when you really learn how to manage an LLM for a complex piece of software far beyond what you have time for, you see the benefits. Try

I have lost a few friends to llm sycophancy induced psychosis wherein they believe, and are encouraged to believe by the llm that, they are the sole individuals who have cracked "prompting", and, in fact, by so doing, have summoned the singularity for their sole benefit and under their sole control. You sound exactly like them.

You sound like the child of a psychotherapist.

Re: GPTs and Feeling Left Behind

#83

Post by lvl155 »

storus wrote: post #5

The worst thing is when LLMs introduce subtle bugs into code and one just can't spot them quickly. I was recently doing some Langfuse integration and used Cursor to generate skeleton code for pushing some traces/scores quickly. The generated code included one parameter "score_id" that was undocumented in Langfuse but somehow was accepted and messed the whole tracking up. Even after multiple passes of debugging I coul…

This is a very important lesson because the way these coding models are built. You have to understand HOW they are designed from the base LLMs. And more importantly why it’s crucial to use two distinctly different models to review each other at every turn.

Re: GPTs and Feeling Left Behind

#84

Post by someoneiam »

myaccountonhn wrote: post #76

I hate AIs because I think overall they're bad for the environment, centralizes power, and worsen quality. That said I never really doubted that they can help you get more done. I use it occasionally to refactor or generate some boilerplate. But very often though I need to rewrite most of the functionality, I find it more true the more code it generates. The agentic stuff I've tried have been terrible. Yeah I persona…

You sound like me. I've found some good uses for them generating ansible files for example (the output is regularly wrong, even with the latest and greatest model, but easy enough to correct). But otherwise, there always seems to be a cutoff in the complexity of a project where the ROI of just having to have built everything myself, and thus being completely immersed in the codebase, seems like it would have been much greater then prompting something to frankensteinian life.

But most of all, I love the act of programming and cannot imagine myself giving that over to an LLM. "Managing" an LLM is to me a soul crushing - maybe anti-intellectual, but definitely boring - task. And if that is what we as professionals will be required to do in the future, I'll just change profession.

Re: GPTs and Feeling Left Behind

#85

Post by ecocentrik »

UltraSane wrote: post #73
bionhoward wrote: post #62

Earlier quoted context omitted.

Cursor has a privacy mode with zero data retention and no training

You have to trust them because their is no way to verify this claim.

Or not trust them because there is not way to verify this claim.

Re: GPTs and Feeling Left Behind

#86

Post by DGCA »

jvanderbot wrote: post #44
martinald wrote: post #20

I'm completely equally lost the other way. I've went through multiple phases of LLM usage for development. GPT3.5 era: wow this is amazing, oh. everything is hallucinated. not actually as useful as I first thought GPT4 era: very helpful as stackoverflow on steroids. Claude 3.5 Sonnet: have it open pretty much all the time, constantly asking questions and getting it to generate simple code (in the web UI) when it goes…

I'm convinced the vast difference in outcome with LLM use is a product of the vast difference in jobs. For front end work it's just amazing. Spits out boilerplate and makes alterations without any need of help. For domain specific backend, for example robotics, it's bad. Tries to puke bespoke a-star, or invents libraries and functions. I'm way better off hand coding these things. The problem is this is classic Gell M…

Frontend dev for 13+ years here. In my experience it’s pretty bad at anything but basic frontend stuff. I’ve tried all the models, editors, Claude code etc.

It’s constantly wrong about the simplest things. Just now it was hallucinating about CSS grid properties.

I’m convinced that how good AI seems is inversely correlated to someone’s knowledge in that domain, as you also mentioned.

Still super useful in my day to day but I have to hand hold and correct it constantly.

Re: GPTs and Feeling Left Behind

#87

Post by tiddles »

Code is a liability. When I let a LLM take the wheel, I end up with thousands of lines of crappy abstractions and needless comments and strange patterns that take way more brain power to understand than if I did it myself.

My current workflow has reverted to primitive copy paste into web chat (via Kagi Assistant). The friction is enough to make me put a lot of thought into each prompt and how much code context I give it (gathered via files-to-prompt from simonw).

I have little experience with frontend and web apps, so I am trying out a supervised vibe coding flow. I give most of the code base per prompt, ask for a single feature, then read the code output fully and iterate on it a few times to reduce aforementioned bad patterns. Normally I will then type it out myself, or at most copy a few snippets of tens of lines.

What doesn’t work I found is asking for the full file with changes applied already. Not only does it take a long time and waste tokens, it normally breaks/truncates/rewords unrelated code.

So far I’m happy with how this project is going. I am familiar with all the code as I have audited and typed it out nearly entirely myself. I am actually retaining some knowledge and learning new concepts (reactive state with VanJS) and have confidence I can maintain this project even without an LLM in future, which includes handing it over to colleagues :)

Re: GPTs and Feeling Left Behind

#88

Post by themafia »

sublinear wrote: post #78
avalys wrote: post #9

I have a degree in CS from MIT and did professional software engineering from 2004 - 2020. I recently started a company in another field and haven’t done any real development for about 4 years. Earlier this summer I took a vacation and decided to start a small software hobby project specific to my industry. I decided to try out Cursor for the first time. I found it incredibly helpful at saving time implementing all t…

I think you're describing what was easily fixed in the past by better docs with examples.

That and better libraries and continued improvements based upon feedback from usage in the field. Then open source very recently took a drastic turn and decided that reimplementing things in a new language was the best way forward, to move fast and break things, and to let the reference implementation _be_ the documentation.

I believe these two facts are connected by the financial interests of the companies that promulgate them. It's easier to believe since their financial interests are so directly entangled.

I feel bad for the author of this article. They're being led down a technological dead end. As always, the top reply to any of these posts, is a bunch of vague and hand wavy explanation as to why the OP is "doing it wrong" and how they're "getting actual value!" Never a link to the actual project or output. Probably because we could all search the produced code, find the prior examples, and once again point out that "AI" is just "copyright whitewashing."

This industry is no longer driven by engineering but by gross financial tricks.

Re: GPTs and Feeling Left Behind

#89

Post by globular-toast »

dbalatero wrote: post #37
8organicbits wrote: post #23

Earlier quoted context omitted.

> This is working well NOW, it will probably not work in 2 weeks, or it will work twice as well. ¯\_(ツ)_/¯ This all feels like spinning the roulette wheel. I sometimes wonder if AI proponents are just gamblers who had the unfortunate luck of winning the first few prompts.

I've seen comparisons to gambling before (activating reward centers, sometimes it pays out big, etc), but couldn't find the article when I searched.

That really resonates. I've found myself questioning whether I'm wasting my time writing a piece of code: what if the LLM could do this more quickly? So I try it, almost every time, and sometimes it does, sometimes it doesn't. Am I really saving myself any work in the long run? Honestly I don't know. I feel like it's just causing me to work more because it feels like a game and that is, ultimately, where the results are coming from.

Re: GPTs and Feeling Left Behind

#90

Post by bobsmooth »

tyfighter wrote: post #24

You're (they're?) not alone. This mirrors every experience I've had trying to give them a chance. I worry that I'm just speaking another language at this point. EDIT: Just to add context seeing other comments, I almost exclusively work in C++ on GPU drivers.

I can't imagine there is a lot of GPU driver code in the training data.
Post reply on HN