←back to thread

Coding with LLMs in the summer of 2025 – an update

(antirez.com)
600 points antirez | 1 comments | 20 Jul 25 11:04 UTC | HN request time: 0.209s | source
Show context
DSingularity ◴[20 Jul 25 15:27 UTC] No.44626096[source]▶
Sorry if I missed it in the article — what’s your setup? Do you use a CLI tool like aider or are you using an IDE like cursor?
replies(2): >>44626136 #>>44626143 #
antirez ◴[20 Jul 25 15:31 UTC] No.44626143[source]▶
Terminal with vim in one side, the official web interface of the model in the other side. The pbcopy utility to pass stuff in the clipboard. I believe models should be used in their native interface as when there are other layers sometimes the model served is not exactly the same, other times it misbehaves because of RAG and in general no exact control of the context window.
replies(2): >>44627385 #>>44681522 #
js2 ◴[20 Jul 25 17:36 UTC] No.44627385[source]▶
This seems like a lot of work depending upon the use case. e.g. the other day I had a bunch of JSON files with contact info. I needed to update them with more recent contact info on an internal Confluence page. I exported the Confluence page to a PDF, then dropped it into the same directory as the JSON files. I told Claude Code to read the PDF and use it to update the JSON files.

It tried a few ways to read the PDF before coming up with installing PyPDF2, using that to parse the PDF, then updated all the JSON files. It took about 5 minutes to do this, but it ended up 100% correct, updating 7 different fields across two dozen JSON files.

(The reason for the PDF export was to get past the Confluence page being behind Okta authentication. In retrospect, I probably should've saved the HTML and/or let Claude Code figure out how to grab the page itself.)

How would I have done that with Gemini using just the web interface?

replies(1): >>44669957 #
1. clscott ◴[24 Jul 25 12:42 UTC] No.44669957[source]▶
Do I understand correctly that you deliberately entered personal contact information into LLM?

If so, I would be a reprimanding anyone in my org that did this. While it’s more effort I’d use the LLM to write a script to read the page with the Confluence api, parse it, write out the json files and push them where they need to go.

Add in basic assertions to check the data is present, in the expected format and there is enough of it. Alerting when the assertions fail, then I can schedule it and forget about it.

This is where LLMs shine, I can now build a robust solution in an hour instead of a day.