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

51–60 of 226 posts

Re: GPTs and Feeling Left Behind

#51

Post by dnh44 »

zhivota wrote: post #48
dnh44 wrote: post #10

Earlier quoted context omitted.

Last summer I came back to software after about 12 years away and I pretty much had an identical experience to you with using AI as a helper to come back. I've now spent the last 6 months coding as much as I can in between consulting gigs. I'm not sure if I would have been able to get caught up so quickly without AI. I haven't had this much fun programming since I was at university hacking away on sun workstations, b…

> I'm currently getting Claude Code to pair program with GPT-5 and they delegate the file edits to Gemini Flash. It's pretty cool. This sounds cool, any more details or any write up on how to do something like this?

I use a program called RepoPrompt to do it. The dev has a video here:

https://www.youtube.com/watch?v=JzVnXzmZweg&t

Re: GPTs and Feeling Left Behind

#52

Post by PessimalDecimal »

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.

A comparison I've seen isn't to roulette but to a slot machine. Anthropic itself encourages its employees to treat its use for refactors as a slot machine. [1]

It seems like an idea worth exploring formally but I haven't see that done anywhere. Is this a case of "perception of winning" while one is actually losing? Or it it that the winning is in aggregate and people who like LLM-based coding are just more tolerant of the volatility to get there?

The only study I've seen testing the actual observable impact on velocity showed a modest decrease in output for experienced engineers who were using LLMs for coding.

[1] https://www-cdn.anthropic.com/58284b19e702b49db9302d5b6f135a...

Re: GPTs and Feeling Left Behind

#53

Post by PaulHoule »

solarkraft wrote: post #30
leptons wrote: post #15

Earlier quoted context omitted.

>I was working on some code where I didn't really understand the typescript types and fed it the crazy error messages I was getting and it made a try to understand them and didn't really, I used it as a "rubber duck" over the course of a day or two and working with it I eventually came to understand what was wrong and how to fix and I got into a place that I like and when there is an error I can understand it and it…

My (not GP) intuitive answer would be hell no. Typescript messages are pretty hard to google and even parse manually and the LLM suggesting multiple approaches and ways to think about the problem does seem useful. It sometimes uncovers unknown unknowns you might never find otherwise. I have had cases in which a web search and some good old fashioned thinking have yielded better results than using an LLM, but on avera…

Personally I think Stack Overflow and Google are 95% trash for that kind of problem.

The answers are in (i) the Typescript documentation and (ii) the documentation of libraries that I'm using. I could get lucky with a Google search and it could be worth trying, but I wouldn't expect it to work. Personally my preference is to have a language and libraries with great documentation (Python, Java, Typescript isn't too bad [1]) and really know that documentation like the back of my hand.

If I hadn't had the LLM I would have probably figured it out the same way doing experiments, I might have asked my other "rubber duck"

https://mastodon.social/@UP8/113935901671533690

A tactic I didn't use, which helps in "legacy" systems where I am stuck, is start a fresh project in the IDE and try either reproducing the problem or building a tiny system which is problem free.

I'm hesitant to say what speedup I got out of the "figuring out the types together with the LLM" but emotionally I felt supported and in the process I wrote a whole lot, like I was keeping track of the process in a notebook. I feel a lot times when I have good LLM conversations I wind up writing better code than I would otherwise, not necessarily write it faster -- it's like pair programming.

[1] The typescript docs are great for the typescript stuff, MDN is good for Javascript and Javascript's stdlib

Re: GPTs and Feeling Left Behind

#54

Post by PaulHoule »

martinald wrote: post #38
kaashif wrote: post #33

Earlier quoted context omitted.

Yeah, as a primarily backend engineer dealing with either weird technical problems Claude can't get quite right or esoteric business domain problems Claude has no idea about (and indeed, it may be only a few people in one company could help with) - Claude isn't that useful. But random stuff like make a web app that automates this thing or make an admin panel with auto complete on these fields and caching data pulled…

One thing I'd recommend for weird business domain projects as a starter is getting it to create a "wiki" of markdown files of all the logic (I suspect this may have been on your to-do list anyway!). You may be pleasantly surprised at how well it does it, and then you can update your claude.md file to point to them (or even put it in there, but it is maybe overkill).

Asking for documentation is good. I had a data structure in Java that was a bunch of nested Map(s) that I partially understood and asked my agent to write me some sample JSON documents and... it just did it and it was a big help for manual coding against that structure.

When I can't figure out something about a library I have often loaded the git repository into my IDE and checked out the version I was using, then used the IDE to study the code. Now I do that and ask the agent questions about the code like "How do I do X?" (often it sees the part in the doumentation that I missed) or "Where is the code that does Y?" It greatly accelerates the process of understanding code.

Re: GPTs and Feeling Left Behind

#55

Post by dnh44 »

1over137 wrote: post #13
dumbmrblah wrote: post #4

I really wish posts like this included the parameters that they were using. What model? What was the question? How many shots? Etc etc You’re going to get vastly different responses if you’re using Opus versus 4o.

I’d like to know which programming language.

I'm of the same opinion as the op and I'm programming in Rust(api) and Swift(client) right now.

I entered a vibe coded game hackathon a few months back and in a little over a week I was at 25k lines of code across both the client and server. It all worked (multiplayer) even though the game sucked.

Re: GPTs and Feeling Left Behind

#56

Post by dang »

jackdawed wrote: post #8

One blogpost I found on HN completely leveled up how I use LLMs for coding: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/ Having the AI ask me questions and think about the PRD/spec ultimately made me a better system designer.

Discussion here:

My LLM codegen workflow - https://news.ycombinator.com/item?id=43094006 - Feb 2025 (160 comments)

Re: GPTs and Feeling Left Behind

#57

Post by hckrfucrs »

calrain wrote: post #42
throwawa14223 wrote: post #27

Earlier quoted context omitted.

So you're taking an easy task, formal logic, and replacing it with a more difficult and time consuming task, babysitting a random number generator. How is that a net-positive?

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.

Re: GPTs and Feeling Left Behind

#58

Post by mitthrowaway2 »

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…

For a hobby project that seems fine, but for commercially valuable work how do you handle privacy concerns?

Re: GPTs and Feeling Left Behind

#59

Post by viccis »

kaashif wrote: post #33
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…

Yeah, as a primarily backend engineer dealing with either weird technical problems Claude can't get quite right or esoteric business domain problems Claude has no idea about (and indeed, it may be only a few people in one company could help with) - Claude isn't that useful. But random stuff like make a web app that automates this thing or make an admin panel with auto complete on these fields and caching data pulled…

I've found that it's mainly good at doing coding work that basically anyone who's memorized the content of the relevant docs could do. So I mostly only use it as glorified scaffolding, as it crashes and burns on complex stuff in big legacy codebases.

Re: GPTs and Feeling Left Behind

#60

Post by jtfrench »

I think the issue is ChatGPT. I find it to be the worst for writing shippable code beyond a single function. It plays too many mind games. If I’m trying to get any non-trivial amount of code done, it’s Gemini Pro 2.5 all the way.
Post reply on HN