LLM Inevitabilism

(tomrenner.com)

1611 points SwoopsFromAbove | 3 comments | 15 Jul 25 04:35 UTC | HN request time: 0.644s | source

Show context

mg ◴[15 Jul 25 05:41 UTC] No.44568158[source]▶

In the 90s a friend told me about the internet. And that he knows someone who is in a university and has access to it and can show us. An hour later, we were sitting in front of a computer in that university and watched his friend surfing the web. Clicking on links, receiving pages of text. Faster than one could read. In a nice layout. Even with images. And links to other pages. We were shocked. No printing, no shipping, no waiting. This was the future. It was inevitable.

Yesterday I wanted to rewrite a program to use a large library that would have required me to dive deep down into the documentation or read its code to tackle my use case. As a first try, I just copy+pasted the whole library and my whole program into GPT 4.1 and told it to rewrite it using the library. It succeeded at the first attempt. The rewrite itself was small enough that I could read all code changes in 15 minutes and make a few stylistic changes. Done. Hours of time saved. This is the future. It is inevitable.

PS: Most replies seem to compare my experience to experiences that the responders have with agentic coding, where the developer is iteratively changing the code by chatting with an LLM. I am not doing that. I use a "One prompt one file. No code edits." approach, which I describe here:

https://www.gibney.org/prompt_coding

replies(58): >>44568182 #>>44568188 #>>44568190 #>>44568192 #>>44568320 #>>44568350 #>>44568360 #>>44568380 #>>44568449 #>>44568468 #>>44568473 #>>44568515 #>>44568537 #>>44568578 #>>44568699 #>>44568746 #>>44568760 #>>44568767 #>>44568791 #>>44568805 #>>44568823 #>>44568844 #>>44568871 #>>44568887 #>>44568901 #>>44568927 #>>44569007 #>>44569010 #>>44569128 #>>44569134 #>>44569145 #>>44569203 #>>44569303 #>>44569320 #>>44569347 #>>44569391 #>>44569396 #>>44569574 #>>44569581 #>>44569584 #>>44569621 #>>44569732 #>>44569761 #>>44569803 #>>44569903 #>>44570005 #>>44570024 #>>44570069 #>>44570120 #>>44570129 #>>44570365 #>>44570482 #>>44570537 #>>44570585 #>>44570642 #>>44570674 #>>44572113 #>>44574176 #

1. blks ◴[15 Jul 25 07:44 UTC] No.44568887[source]▶

>>44568158 #

So how big was the library? If I understood correctly, it was a single file library (with hours worth of documentation)? Or did you go over all files of that library and copy it file by file?

replies(1): >>44568980 #

2. nosianu ◴[15 Jul 25 08:00 UTC] No.44568980[source]▶

>>44568887 (TP) #

Funny you use something the author of the linked post talks about at the start. This is one of those debate methods. Reframe what was said!

I don't remember that the OP claimed that all problems are solved, perfectly. Do you think by showing examples where AI struggles you really show their point to be wrong? I don't see that.

I use AI only sparingly, but when I do I too experience saving lots of time. For example, I'm only superficially familiar with MS Excel or Power Query scripting APIs and function names. Too bad I've become the got-to point for little mean problems for colleagues. Instead of having to read lots of docs and do lots of trial and error, I now formulate what I want to ChatGPT, give it the file, and thus far I have always received the solution, a transformed file. Sure, anyone regularly using Excel/Power Query could have written the few lines of code easily enough, but since I don't, and don't plan to, being able to use plain language and let the AI do the actual coding is a huge time saver.

For SOME problems in this world it works. Nobody claimed anything you seem to be trying to argue against, that it solves ALL problems, so that finding one or a few counter-examples where it fails invalidates the argument made. And the problems it does solve are not trivial and that it works is quite miraculous and was not possible before.