I went through the motions. There are various points in the repo history where compilation is possible, but it's obscure. They got it to compile and operate prior to the article, but several of the PRs since that point broke everything, and this guy went through the effort of fixing it. I'm pretty sure you can just identify the last working commit and pull the version from there, but working out when looks like a big pain in the butt for a proof of concept.

embedding-shape 6 hours ago | parent [-]

> but several of the PRs since that point broke everything, and this guy went through the effort of fixing it. I'm pretty sure you can just identify the last working commit and pull the version from there, but working out when looks like a big pain in the butt for a proof of concept.

I went through the last 100 commits (https://news.ycombinator.com/item?id=46647037) and nothing there was working (yet/since). Seems now after a developer corrected something it managed to pass `cargo check` without errors, since commit 526e0846151b47cc9f4fcedcc1aeee3cca5792c1 (Jan 16 02:15:02 2026 -0800)

	▲	observationist 5 hours ago \| parent [-]
		There are conversations elsewhere - I'd have to go look through them, but at some point about an hour before the article was published, it could be compiled, and then things got pushed that broke it again? There's no central discussion, I had to piece together information from multiple threads. Sorry, I should have taken notes, lol. At any rate, it was so much digging around I just gave up, I didn't want to invest more effort into it. I figured they'd get a stable version for others to try and I'd return to it at some point.