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

171–180 of 226 posts

Re: GPTs and Feeling Left Behind

#171

Post by tptacek »

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.

What part of this prompt reads like "spellcasting" to you?

Re: GPTs and Feeling Left Behind

#172

Post by martinald »

socalgal2 wrote: post #161
jama211 wrote: post #154

Earlier quoted context omitted.

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.

And the tests? To me, if it was something important enough to have tests for in which case it's important to check the tests are valid so I'd have to review them

It takes me 5 mins to review e2e UI tests and watch it go through them. It's literally filling fields and making sure certain things happen.

Re: GPTs and Feeling Left Behind

#173

Post by martinald »

jama211 wrote: post #156
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…

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.

Exactly. _So much_ software dev is "throwaway" in my experience. Of course some isn't. Landing pages, A/B tests, even a lot of feature work is very speculative and gets put in the trash.

I do wonder if this is why there is such a gulf in LLM experience. If you're doing hardcore huge scale distributed systems then I can (maybe?) see why you'd think it is useless. However, that is very niche imo and most software dev work is some level (unfortunately) of virtually throwaway code. Of course, not all is - of all the ideas and experiments, some percentage is hopefully very successful and can be polished.

Re: GPTs and Feeling Left Behind

#174

Post by bastawhiz »

> I’m in a state where I can’t reconcile my own results with other people’s results. I hear people saying “this hammer is indestructible”, but when I pick it up, it’s just origami: made of paper, intricate, delicate, very cool-looking but I can’t even hammer a tomato with it.

This is a really interesting signal to me. It's almost indisputable that you can get good results (I get good results pretty consistently) and so there's definitely something there. I don't think that folks who don't get good results are doing something "wrong" so much as not understanding how to work with the model to get good results.

If I was at a company building these tools, the author would be the person I'd want to interview. I doubt it's a skill issue. And it's definitely not user error. You can't sell a tool that is said to do something but the user can't replicate the result.

A tool that works but only after you've invested lots of time working to reverse engineer it in your head isn't a good tool, even if it's extremely powerful. The tool needs to be customizable and personalizable and have safety rails to prevent bad results.

Re: GPTs and Feeling Left Behind

#177

Post by DGCA »

anonzzzies wrote: post #101
DGCA wrote: post #86

Earlier quoted context omitted.

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 da…

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…

Are you implementing designs that were given to you or having AI generate the design as well? I could see it being better at the latter.

Re: GPTs and Feeling Left Behind

#178

Post by PlunderBunny »

tptacek wrote: post #170
godelski wrote: post #169

Earlier quoted context omitted.

> but it saved me from a bunch of tedious work that I don’t enjoy anyway. I play music and find practicing scales and learning music theory much more tedious and less enjoyable. I'd much rather be playing actual songs and having that flow where it is like the music is just coming out of me. But the reason I do the tedious stuff is because I don't get the latter stuff without the former. I can still learn to play song…

I'm having trouble with this sentiment, because most progress in programming environments involves eliminating and automating away drudgery. The analogy you're making to playing scales and learning music theory applies just as much --- maybe even more so --- to automated memory management!

Not necessarily disagreeing with your points, or the general argument, but I think the trade-offs and consequences of choosing a language with automated memory management are reasonably well understood, and manageable, but can we say the same about vast amounts of AI written code?

Re: GPTs and Feeling Left Behind

#179

Post by tptacek »

PlunderBunny wrote: post #178
tptacek wrote: post #170

Earlier quoted context omitted.

I'm having trouble with this sentiment, because most progress in programming environments involves eliminating and automating away drudgery. The analogy you're making to playing scales and learning music theory applies just as much --- maybe even more so --- to automated memory management!

Not necessarily disagreeing with your points, or the general argument, but I think the trade-offs and consequences of choosing a language with automated memory management are reasonably well understood, and manageable, but can we say the same about vast amounts of AI written code?

Automated memory management was fiercely debated at the time. So were high-level programming languages, so much so that Paul Graham was moved to write "Beating the Averages".

Re: GPTs and Feeling Left Behind

#180

Post by PlunderBunny »

tptacek wrote: post #179
PlunderBunny wrote: post #178

Earlier quoted context omitted.

Not necessarily disagreeing with your points, or the general argument, but I think the trade-offs and consequences of choosing a language with automated memory management are reasonably well understood, and manageable, but can we say the same about vast amounts of AI written code?

Automated memory management was fiercely debated at the time. So were high-level programming languages, so much so that Paul Graham was moved to write "Beating the Averages".

Fair enough - I wasn't there at the time. Perhaps (obviously?) we're still at the debating stage of AI assisted coding. But I think we can say we now understand the trade-offs etc around memory managed languages.
Post reply on HN