zlacker

>>tablet+(OP)
"If you’re making requests on a ChatGPT page and then pasting the resulting (broken) code into your editor, you’re not doing what the AI boosters are doing. No wonder you’re talking past each other."

This is in fact what I am doing (though I am not trying to convince anyone not to use LLMs). How can I get into this other mode? Any pointers? Do I need to pay up for a service? I do not want to carry out vibe coding, I want to use LLMs to solve physics, math and logic problems/puzzles. I'd appreciate any recommendations.

>>atakan+j51
Just have a look at Cursor.ai or zed.dev. Cursor is based on VS Code and integrates different models right into your codebase. It has access to your codebase, knows your code (after indexing) and is able to directly apply changes to your code or run commands on your integrated terminal. You can directly accept/decline changes. You can reference existing code / files. You can link documentation, you can write a default prompt and default settings (previously .cursorrules).

It's faster than opening chatgpt in browser, writing your promt, waiting for the reply, scanning and scrolling through the reply, copying it, inserting it manually, going back to say something doesn't work.