Caveman

I use terminal commands to open relevant ide for the project

Having a bunch of plugins built-in means also supported in updates and play nice with each other

I also had issue when I was working on a pycharm project back when I was on windows. During setup it asked me “What’s your name?” and my name has a cheeky accent which Windows was decided should be the name of my Home folder. Home folder also has appdata and whatnon so which the build system didn’t expect to have a an accent in the folder path.

I ended up having to create a different folder and link to it then move all the path configurations to that folder link just so I could get imports working.

I use Jetbrains IDEs now for 5 years, I’ve used VSCode, Sublime, Atom, Vim, Neovim but I feel like Jetbrains IDEs are just better if you have the RAM to run it.

1. It’s a setting.
2. Doesn’t happen
3. Doesn’t happen
4. Searchable actions, just search for “encoding” in this case.
5. That’s an LSP/project mismatch usually just a setting. Most things are supported but worst case you can remove the error.
6. Happens if you run out of RAM or open a very large file.

So it’s not all bad, but comes with a lot of good such as “invert if statement”, “use template strings” and “extract method” thingies along with a load of plugins.

Don’t get me wrong, I still write more than 98% of code by hand and of course, I can write those functions myself in 30m myself but I can get it in 60s with the AI. LLMs can write code to that does parse - > model - > map - > format with only one or two easy to fix bugs.

It’s in the very niche cases where it’s just tedious to write something out that LLMs actually work. “Write an API client that uses [library] that handles these requests/responses” comes also to mind as something that would work.

I’m using now also to learn react native where I get bugs I’m very unfamiliar with and SO doesn’t give me a good answer.

I’ve also had decent success at having it review my code with “how would I further optimise this code” and it gives me some pointers and then writes buggy code but the approach is correct usually and I can implement it myself.

These AIs really suck at writing correct code but I’ve had good success in having them write code generators. I recently made it write a script that takes a SQL create table statement and converts in to TS and gives insert update, delete and whatnot and also creates a simple class that handles the operations.

I had to write the original code by hand but having it write code that writes boilerplate which I correct is pretty good.

Other code is hit or miss IMO

My answer aged like milk

FF is doing great. All the have to do now is the Steam strategy. Do nothing and wait for the competition to fuck themselves over.