LLMs are kind of fun to play with (this is a website for nerds, who among us doesn’t find a computer that talks back kind of fun), but I don’t really understand why people pay for these hosted versions. While the tech is still nascent, why not do a local install and learn how everything works?

Because my local is a laptop and doesn't have a GPU cluster or TPU pod attached to it.

Claude code with opus is a completely different creature from aider with qwen on a 3090.

The latter writes code. the former solves problems with code, and keeps growing the codebase with new features. (until I lose control of the complexity and each subsequent call uses up more and more tokens)