

Personally, LLMs are too often wrong and overly confident to be useful for me. Plus, unless you’re running a local model, yet another subscription is not fun, especially by the likes of OpenAI and Anthropic. And you have all the ethical issues with LLMs that I’m sure you’ve heard about already.
It would be much better if you used the vast swath of online resources we are very lucky to have nowadays, don’t take it for granted as the internet becomes increasingly saturated with low-effort LLM generated garbage.
Again, the only scenario where LLMs are potentially useful is translation in my opinion, and even then, you have to mindful it is often pretty wrong.






I find it’s an in between of something like nano vs VSCodium or Zed. It works well for editing single files + has features like syntax highlighting and such, but it is not as powerful as other code editors. And the editors I have mentioned are a step down again from full IDEs (which do their job very well with all the features you could want for debugging and whatnot)
Kate isn’t a bad code editor, I think it does the job while being relatively lightweight compared to VSCodium and especially full IDEs. Zed is very quick so I’ve mostly replaced Kate (and VSCodium) with that, but Kate is an awesome piece of software too!