Can that scale down to individual .cpp files though? My understanding was that it works more at the package level.

I don't think that's unique to LLMs though. Traditional learning material is very often like that too, and I actually find it worse because you can't ask it questions.

You need a project that you want to achieve. Maybe automating something, or some kind of Arduino thing? The latter might be especially good for learning because you can't trivially delegate it to AI, but you can still ask AI for help.

How much are they offering? 😄

The latest models are capable of non-slop code and tolerable prose (OpenAI is much better than Anthropic on the prose but I think Anthropic has a slight edge on code quality). It's really just pre-Astra models that are super sloppy. Annoyingly you get what you pay for.

Also the benchmarks don't really seem to capture this at all. I guess it is difficult to have a benchmark for code quality or writing style.

Ooo interesting, I didn't know that!

Ugh I really wish they'd support something less awful than GNU linker scripts. You should be able to write linker scripts in Starlark or something.

Might have helped the introduction if you said what you are talking about...

Here are the top 5

The top 5 what?

Looks like it should just work, right? On stable it doesn't, and it trips twice.

"Trips" does it Claude? 🤨

Rust is pretty great in almost all domains. The only ones where I think Python is a sensible choice are research, where a REPL is really useful (think Jupyter).

There are plenty of things that are "scripting", i.e. ad-hoc admin of other projects that aren't actually Python projects, where you want to share code between multiple scripts.

Rust has scripting support. It's nightly only but that's not actually a big deal since running nightly is trivial.

It has some limitations currently, but... so does Python.

Pairwise ranking is definitely better than stars, but nobody wants to read your slop, sorry.

Google shows there are lots of these already: Flickchart, Canonova (slop), moup.app (also slop), popcornlist (possibly slop but they at least wrote their own prose so they get a pass, though it is an iPhone app only), pairckle (generic pairwise ranking, not slop!)

Also it doesn't sound like you have figured out how to actually do the ranking yet. Look up Bradley-Terry or TrueSkill.

As usually, the difficult bit is getting users.