Ask HN: Those with success using GPT-4 for programming

Re:Ask HN: Those with success using GPT-4 for programming – ... by vitorbaptistaa on Monday May 22, 2023 @06:51PM (#36037697)

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 think maybe once or twice the code didn't compile (I used it dozens of times per day).

I'm now using the optimized Go code in production.

[ Parent | on HN ]

Re:Ask HN: Those with success using GPT-4 for programming – ... by bredren on Monday May 22, 2023 @07:36PM (#36038061)

What kind of memory efficiency gains did you see as a result of the effort?

[ Parent | on HN ]

Re:Ask HN: Those with success using GPT-4 for programming – ... by vitorbaptistaa on Wednesday May 24, 2023 @06:51AM (#36056236)

I didn't keep track of the benchmarks very well. However, it went from taking 3+ days and 180GB of memory to process 80M rows [1] to processing 1.3B rows in ~6 hours using ~90GB of memory.

[1] I stopped the process early, as it was taking too long

[ Parent | on HN ]

Re:Ask HN: Those with success using GPT-4 for programming – ... by superbiome on Tuesday May 23, 2023 @09:58AM (#36044387)

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

[ Parent | on HN ]