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

151–160 of 226 posts

Re: GPTs and Feeling Left Behind

#151

Post by dnh44 »

ModernMech wrote: post #147
dnh44 wrote: post #124

Earlier quoted context omitted.

These are some of the things I do to try and get good results: - I prime the context of the LLM with any extra rules or instructions I want it to follow. - I also prime the context with every single file it needs to see in order to be able to do its job properly. Sometimes this can be two files but sometimes it can be 15 files. - I instruct the LLM in bullet point format for smaller edits. For larger edits I ask the…

This sounds less like engineering advice and more like spellcasting advice.

Yeah it is a bit isn't it

Re: GPTs and Feeling Left Behind

#152

Post by notjoemama »

thrown-0825 wrote: post #105
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.

it really only works for problem domains saturated with medium blogspam and youtube tutorials.

That's a bingo! Christoph Waltz is just a great actor.

I'm building an app in my stack with fairly common requirements. There are a few code examples that cover requirements but none that cover our specific scenario. After searching the web myself, I asked 3 different AI models. All they did was regurgitate the closest public GitHub example, lacking the use case I was trying to do. Solving this problem can only be done by understanding the abstraction of the alteration in design.

These things can't actually think. And now they're allowed to be agentic.

In some ways they're just glorified search engines but there's a geopolitical sprint to see who can get them to mock "thinking" enough to fool everybody.

Out of ego and greed, everything will be turned over to this machine, and that will be the end of humanity; not humans...humanity.

Re: GPTs and Feeling Left Behind

#153

Post by sakopov »

As someone who's been "vibe-coding" successfully at work I can say that what made me a believer in AI tools is agentic instructions. It is the difference between not being able to accomplish much and actually getting stuff done. There have been several articles published on this topic on HN. I would really recommend implementing that in your repositories.

Re: GPTs and Feeling Left Behind

#154

Post by jama211 »

socalgal2 wrote: post #95
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…

> This took less than an hour while I was watching TV. I certainly could not review all of those changes in an uninterupted hour. I'd need to test the design changes on multiple browsers, check they respond to zoom and window sizing. I'd have to read through the tests and check that they were not just nonsense and returning true to pass. There's no way I could do all that while watching TV in 1 hour.

This is for a janky backend admin panel, not a customer facing product. If it’s way better than it was before, which likely wasn’t responsive either, it’s a win. Understanding the context of a project is important.

Re: GPTs and Feeling Left Behind

#155

Post by jama211 »

thunky wrote: post #137
dreadnip wrote: post #111

Earlier quoted context omitted.

I guess the main takeaway is that you don’t care about the quality of the generated code. The end result is all that matters. If I ask it to “add drag & drop”, I already know in my mind what the correct code should look like, because I’ve implemented it many times in the past. LLMs just never deliver the -code- that I want. The end result might look ok and the drag & drop will work, but the code will be atrocious and…

> This is what I’m being paid for right? That's a good question. Because developers can sometimes have a bit of an unhealthy love affair with their own code. Does your employee actually care as much about code quality as much as you do? They would probably ask what is the downside of accepting this lower quality code, given the upside you presented: > The end result might look ok and the drag & drop will work Which y…

Well said.

Re: GPTs and Feeling Left Behind

#156

Post by jama211 »

dreadnip wrote: post #111
anonzzzies wrote: post #101

Earlier quoted context omitted.

I am very bad at frontend and I know frontend peeps keep saying claude/llms are bad at it, but now, for the first time in my 40 year career, I deliver frontend that are looking better and functioning better than whatever I see in hip products people 'designed with love in blah'. And our clients agree. If the css is correct or not, I don't know as I never really found the energy to learn it and now I don't need to and…

I guess the main takeaway is that you don’t care about the quality of the generated code. The end result is all that matters. If I ask it to “add drag & drop”, I already know in my mind what the correct code should look like, because I’ve implemented it many times in the past. LLMs just never deliver the -code- that I want. The end result might look ok and the drag & drop will work, but the code will be atrocious and…

No, you’re being paid to deliver the product to the _company’s_ chosen standards, not yours. And in my experience, fast and cheap and cheerful is often exactly what they want. They’ll have changed their minds next week and want it all ripped out for something else anyway.

Re: GPTs and Feeling Left Behind

#157

Post by jama211 »

VladVladikoff wrote: post #36
throwawaysleep wrote: post #34

Earlier quoted context omitted.

> while I was watching TV This to me is one of the real benefits. I can vibe code watching TV. I can vibe code in bed. I can vibe code on the plane waiting for takeoff with GitHub Copilot Agents.

To me this is sad. I love programming. It was always a fun job. I don’t want to watch TV instead of programming.

Then code personal projects while you vibe code your job. The thing about having more free time, is you can use it on whatever you want.

Re: GPTs and Feeling Left Behind

#158

Post by jama211 »

ath3nd wrote: post #108
rediscovery wrote: post #93

Earlier quoted context omitted.

Behavioral psychology goes a long way in explaining the weird distribution of responses to using LLMs to generate code: "Gambling-like behavior in pigeons: ‘jackpot’ signals promote maladaptive risky choice" https://www.nature.com/articles/s41598-017-06641-x The tech industry is actively promoting gambling addiction and the scary thing is that people are willingly walking into that trap. Take a look at this comment:…

Very insightful. You are not alone: https://rgoldfinger.com/blog/2025-07-26-claude-code-is-a-slo... > Are we at the point of doing rain dances for these models and describing the moves as "counterintuitive and sublte" Yes, we are. LLM cultists can downvote as much as they like, but the reality is that with all the incantations and coaxing, we not only don't see a positive effect, we see a net negative effect on the q…

And like plastic, a fantastic material for many jobs, it’s just has its own pros and cons

Re: GPTs and Feeling Left Behind

#159

Post by jama211 »

ath3nd wrote: post #108
rediscovery wrote: post #93

Earlier quoted context omitted.

Behavioral psychology goes a long way in explaining the weird distribution of responses to using LLMs to generate code: "Gambling-like behavior in pigeons: ‘jackpot’ signals promote maladaptive risky choice" https://www.nature.com/articles/s41598-017-06641-x The tech industry is actively promoting gambling addiction and the scary thing is that people are willingly walking into that trap. Take a look at this comment:…

Very insightful. You are not alone: https://rgoldfinger.com/blog/2025-07-26-claude-code-is-a-slo... > Are we at the point of doing rain dances for these models and describing the moves as "counterintuitive and sublte" Yes, we are. LLM cultists can downvote as much as they like, but the reality is that with all the incantations and coaxing, we not only don't see a positive effect, we see a net negative effect on the q…

Also in general I find developers usually overestimate the value of good code outside of mission critical systems. The true value return of spending way more time and effort to improve code quality often simply isn’t worth it from a holistic perspective.

Re: GPTs and Feeling Left Behind

#160

Post by jama211 »

This isn’t a post, this is just a random opinion. Also, if they can code a small web app faster than an llm can I’ll eat my hat. I’d like to see them try and write the 2000+ lines required to get it up and running in less than 30 seconds.

Seems like their attitude is exactly what you’d expect of someone who wants it to be useless from the outset. A self fulfilling hypothesis.

Post reply on HN