I've been using Open Interpreter quite a bit in building a React website. If you haven't heard of it, Open Interpreter lets LLMs run code on your computer to complete tasks. This has a major advantage over the average AI web interface in that it can see entire directories rather than being limited to a code snippet or single page. I admit it has been a while since I used Copilot, so I'm not sure if it has that capability yet. However, Open Interpreter also has the ability to run apps and take over your screen/keyboard, among some other really cool things.
I'm using WSL and it works great. Here's a quick setup guide:
Create a virtual environment
python -m venv venv
Activate it
source venv/bin/activate
Install Open Interpreter
pip install open-interpreter
Start the interpreter
interpreter
Some additional notes
- You will need an OpenAI API key, so head over to their site if you don't have one yet.
- There are many flags and custom prompts that can be used; head over to the official documentation for further use: Open Interpreter Documentation.
- In WSL, conversations are saved in
/home/user/.config/open-interpreter/conversations
. - The list of supported models can be found here: Supported Models.
I've been really impressed with GPT-4O, but I'd love to hear about others' experiences.
Top comments (0)