Comment by originalvichy

Most of the things I've used LLMs for is scripting code for integrations between systems, or scripts that extract and transform data from APIs.

For this specific use case, LLMs and their integrations with tools like VSCode have been excellent. A simple instruction file dictating what libraries to use, and lines about where to look for up-to-date API docs, increases the chances of one-shots significantly.

My favorite part has been that I'm able to use libraries I wouldn't have used previously like openpyxl. A use case like "get data from an API, transform it, and output it to an excel file with these columns" is super fast, and outputs data to a stakeholder/non-techy format.

It made me chuckle when Claude etc. release Excel integrations, since working with Excel files seems to have been at a great stage for people who've already worked with Excel/CSV libraries.

The number 1 suggestion I'd have for people eager to work with text is to use models to learn about old unix tools like grep/sed etc. With these powerful tools + modern tools + code you can build quite complex integration code for many uses. Don't sleep on the classic unix cli commands and download stuff from github to achieve things that have already been solved 40 years ago :)