←back to thread

Coding with LLMs in the summer of 2025 – an update

(antirez.com)
600 points antirez | 2 comments | 20 Jul 25 11:04 UTC | HN request time: 0.001s | source
Show context
qweiopqweiop ◴[20 Jul 25 13:33 UTC] No.44625068[source]▶
This matches my take, but I'm curious if OP has used Claude code.
replies(1): >>44625079 #
1. antirez ◴[20 Jul 25 13:36 UTC] No.44625079[source]▶
Yep when I use agents I go for Claude Code. For example I needed to buy too many Commodore 64 than appropriate lately, and I let it code a Telegram bot advising me when popular sources would have interesting listings. It worked (after a few iterations) then I looked at the code base and wanted to puke but who cares in this case? It worked and it was much faster and I had zero to learn in the proces of doing it myself. I published a Telegram library for C in the past and know how it works and how to do scraping and so forth.
replies(1): >>44625177 #
2. Keyframe ◴[20 Jul 25 13:49 UTC] No.44625177[source]▶
For example I needed to buy too many Commodore 64 than appropriate lately

Been there, done that!

for those one-off small things, LLMs are rather cool. Especially Cloude Code and Gemini CLI. I was given an archive of some really old movies recently, but files were bearing title names in Croatian instead of original (mostly English ones). So I claude --dangerously-skip-permissions into the directory with movies and in a two-sentence prompt I asked it to rename files into a given format (that I tend to have in my archive) and for each title to find original name and year or release and use it in the file.. but, before commiting rename to give me a list of before and after for approval. It took like what, a minute of writing a prompt.

Now, for larger things, I'm still exploring a way, an angle, what and how to do it. I've tried from yolo prompting to structured and uber structured approaches, all the way to mimicking product/prd - architecture - project management / tasks - developer/agents.. so far, unless it's rather simpler projects I don't see it's happening that way. Most luck I had was "some structure" as context and inputs and then guiding prompting during sessions and reviewing stuff. Almost pair-programming.