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

Ask HN: Those with success using GPT-4 for programming – what are you doing?

news.ycombinator.com

Post reply on HN
Print view View original

81–90 of 109 posts

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#81

Post by algo_trader »

rtcode_io wrote: post #74

https://RTEdge.net was polished up in no time, thanks to its vast knowledge. If you're knowledgeable in the field you ask questions about, it becomes a pure time save, as you can either just tell or test it. It's general world knowledge is also vastly impressive though. It can draw a 2D representation of a keyboard key _____________ | | | Keycaps | |___________| | | | Key Switch| |___________| | | | Circuit | | Board…

RTEdge looks very nice

What exactly is being shown on the map ?

And which libs did u use ?

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#82

Post by itaileibowitz »

I documented my process of building an email-auto responder with ChatGPT, not even GPT-4: https://dearai.substack.com/p/coding-gabrielle-six-chatgpt-s...

I only have a little coding background, and ChatGPT didn't make me an expert. But the collaborative Human+AI process did allow me to complete a project end-to-end, including figuring out where to host it and how to do that.

I found that it helped me with 6 "superpowers": 1. Choosing between options (e.g., AWS vs. GCP vs. Zapier) 2. Walk me through it (e.g., how to set up a Firestore database) 3. Text-to-code (including simple nuisance calculations and code-to-code changes) 4. Help me out! (i.e., fixing broken code based on error messages) 5. Teach me (e.g., learning the difference between let, const, var, etc...) 6. Check my code (e.g., it caught errors before I even ran the code)

Check out the post for more details if you'd like!

There's another post on building a website from scratch where I also tried Replit's Ghostwriter. Yes, I faced a lot of frustrations in the process, but going from "I can try struggle through this on my own" to "I actually have some help here that's always available and usually right" is amazing IMO.

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#83

Post by reaperman »

soco wrote: post #80
reaperman wrote: post #23

Earlier quoted context omitted.

I've also been using ChatGPT to create SQL queries -- it's genuinely really, really great at this. I do have to say "I'm using PostgreSQL with DataGrip IDE" and feed it back any errors I get, because there are a lot of permutations for SQL, but it's a pretty seamless experience overall. Here's an example of one that helped me a lot. This takes no time at all to get ChatGPT to generate by giving it anonymized snippets…

Maybe you're using the paid version, or I suck too much at prompting, but so far I wasn't able to rely on the generated SQL and not for lack of trying. Workable queries, yes, but never doing what I intended...

I use ChatGPT-4 for $20/month. It pays for itself many times over, it's not really a hard decision at all! And yes, GPT-4 is much better at coding.

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#84

Post by itaileibowitz »

FrostKiwi wrote: post #70

Also had it hallucinate absolute garbage from time to time. The worst offender, that consistently shows up: Claiming there are certain library features, when there are not. Easily the best rubber ducky though. Copy pasting big blocks of my own code and asking about it gives new perspectives to problems I am stuck on. Huge time saver in that regard.

Oh yeah, I agree with that worst offender - features that don't exist that it quotes so confidently.

Especially when libraries get updated constantly - I ran into cases where it wrote functions based on previous versions of the library, where the function names and signature had already changed since.

I haven't tried yet, but I bet if I used a version that has web browsing and can read the latest documentation, it would do a good job and save me having to read the documentation myself and try to work it out.

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#85

Post by superbiome »

vitorbaptistaa wrote: post #8

I had to optimize some Python code to reduce its memory usage. After trying all ideas I could think of, I thought about rewriting it in a different language. Copied and pasted the code into ChatGPT 4. Tried Rust at first, but there were too many compilation errors. Then I tried Go and it worked perfectly. For the next couple of weeks, I used it to improve the Go code, as I've never used Go. It gave me great answers,…

I default to immediately asking GPT4 to review its solution and fix any mistakes it finds.

There’s also an interesting paper about providing it guidance that it can make a “tree of thoughts” which allows it to move forward and backwards as it comes up with solutions then present its best solution to you. The paper suggests you can squeeze a lot more performance out of LLM’s (even smaller ones) this way. I’ve been wanting to experiment with my prompting in this fashion: https://arxiv.org/pdf/2305.10601.pdf

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#87

Post by qingcharles »

soco wrote: post #80
reaperman wrote: post #23

Earlier quoted context omitted.

I've also been using ChatGPT to create SQL queries -- it's genuinely really, really great at this. I do have to say "I'm using PostgreSQL with DataGrip IDE" and feed it back any errors I get, because there are a lot of permutations for SQL, but it's a pretty seamless experience overall. Here's an example of one that helped me a lot. This takes no time at all to get ChatGPT to generate by giving it anonymized snippets…

Maybe you're using the paid version, or I suck too much at prompting, but so far I wasn't able to rely on the generated SQL and not for lack of trying. Workable queries, yes, but never doing what I intended...

I only just got access to the Plus version. But for the last month or so I've been using the free version with absolutely no problems in the scripts it generates.

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#88

Post by kleer001 »

Bostonian wrote: post #71
mkmk wrote: post #5

Adobe automations are written in a truly bizarre language that, among other things, starts counting at 1 instead of 0. ChatGPT cheerfully obliges.

Fortran, Matlab, R, and Julia are a few languages than count from 1 instead of 0. It's not bizarre to do so.

Now, starting to count from -1... that's a horse of a different color

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#89

Post by cetinsert »

algo_trader wrote: post #81
rtcode_io wrote: post #74

https://RTEdge.net was polished up in no time, thanks to its vast knowledge. If you're knowledgeable in the field you ask questions about, it becomes a pure time save, as you can either just tell or test it. It's general world knowledge is also vastly impressive though. It can draw a 2D representation of a keyboard key _____________ | | | Keycaps | |___________| | | | Key Switch| |___________| | | | Circuit | | Board…

RTEdge looks very nice What exactly is being shown on the map ? And which libs did u use ?

https://RTEdge.net

is our global, multi-cloud network! We build on this foundation, a real-time coding/hosting platform using nothing but the web standards and APIs.

On the map, you can click on the nodes and edges (lines) for additional info! This map will be embedded into our marketing pages, which we are in the process of writing.

---

As a teaser, watch https://rt.ht/yt (20s video about RTCode.io – a web playground with reload-free, 2-way input ⇄ output sync; service workers user can code in-editor ( https://sw.rt.ht/?io ) and deploy to the Cloudflare's network ( https://sw.rt.ht ), and other features)!

Re: Ask HN: Those with success using GPT-4 for programming – what are you doing?

#90

Post by Kim_Bruning »

Ha, yeah, GPT* sucks for nixos. I think this is due to

* NixOS development being pretty high paced, [with certain developments (like flakes) post-dating the original GPT cutoff still?]

* Documentation being slow to show up on the internet.

* Just in general lower popularity (than windows or ubuntu or etc) leading to less data for ChatGPT to pick up on.

Post reply on HN