It’s interesting because my career went from doing higher level language (Python) to lower language (C++ and C). Opus and the like is amazing at Python, honestly sometimes better than me but it does do some really stupid architectural decisions occasionally. But when it comes to embedded stuff, it’s still like a junior engineer. Unsure if that will ever change but I wonder if it’s just the quality and availability of training data. This is why I find it hard to believe LLMs will replace hardware engineers anytime soon (I was a MechE for a decade).

▲

necovek 4 hours ago | parent | next [-]

As someone who did Python professionally from a software engineering perspective, I've actually found Python to be pretty crappy really: unaware of _good_ idioms living outside tutorials and likely 90% of Python code out there that was simply hacked together quickly.

I have not tested, but I would expect more niche ecosystems like Rust or Haskell or Erlang to have better overall training set (developer who care about good engineering focus on them), and potentially produce the best output.

For C and C++, I'd expect similar situation with Python: while not as approachable, it is also being pushed on beginning software engineers, and the training data would naturally have plenty of bad code.

	▲	piker an hour ago \| parent \| next [-]
		I have found them all to be pretty useless on my 50k LOC Rust project. They can definitely move forward, but they spew pretty bad code that I usually throw away. I do try though. [NOTE: This is just using "agent mode" with the Co-pilot VS code extension. I haven't tried Cursor or Codex, etc. Also they're tremendously helpful for rubber ducking and debugging.]
	▲	jeremyjh 2 hours ago \| parent \| prev [-]
		I think its pretty good at Elixir, so that tracks.

▲

n_u 7 hours ago | parent | prev | next [-]

I've found it's ok at Rust. I think a lot of existing Rust code is high quality and also the stricter Rust compiler enforces that the output of the LLM is somewhat reasonable.

	▲	raincole an hour ago \| parent \| next [-]
		Quite sure it's not about the language but the domain.
	▲	lemagedurage 5 hours ago \| parent \| prev [-]
		Yes, it's nice to have a strict compiler, so the agent has to keep fixing its bugs until it actually compiles. Rust and TypeScript are great for this.

▲

trenchgun 3 hours ago | parent | prev | next [-]

LLMsdo great with Rust though

▲

ex-aws-dude 9 hours ago | parent | prev | next [-]

I've had a similar experience as a graphics programmer that works in C++ every day

Writing quick python scripts works a lot better than niche domain specific code

▲

nullpoint420 8 hours ago | parent [-]

Unfortunately, I’ve found it’s really good at Wayland and OpenGL. It even knows how to use Clutter and Meta frameworks from the Gnome Mutter stack. Makes me wonder why I learned this all in the first place.

	▲	Trufa 7 hours ago \| parent [-]
		To being able to determine it's really good.

▲

ipnon 4 hours ago | parent | prev | next [-]

I think the combinatorial space is just too much. When I did web dev it was mostly transforming HTML/JSON from well-defined type A to well-defined type B. Everything is in text. There's nothing to reason about besides what is in the prompt itself. But constructing and maintaining a mental model of a chip and all of its instructions and all of the empirical data from profiling is just too much for SOTA to handle reliably.

▲

imposter 7 hours ago | parent | prev [-]

[dead]