I knew the second Eric posted about releasing Slug to the public domain we'd get 100s of "OpenSlug" slopped-up. Will be interesting to see which implementation will win or if Slug will keep being a thing.
Tbf, the Github repo doesn't look particularly 'sloppy' to me, more like some mild AI assistance. There's several months of fairly regular looking git history, a couple of commits with an LLM disclaimer for python bindings, and two llm-context files.
Yeah, I (author) regularly use AI (anyone who doesn't is ... well, they're not seeing the same reality I am, anyways :)), but I don't just "turn it loose." It reviews my initial passes, catches stupid mistakes I make, and often has good advice about "Hey, don't overengineer this", although I _do_ have to regularly reign it in from other complete nonsense (which kind of makes me happy, because it means, you know, I still have a job). For slughorn, it mostly did some of the C++ tests, almost all of the pytest coverage, the pybind docstrings, and the GLFW example (since I do 99% of my own testing with OSG until I finish there and move on to Vulkan).
logdahl · · focus · HN ↗
flohofwoe · · focus · HN ↗
<a href="https://github.com/AlphaPixel/slughorn" rel="nofollow">https://github.com/AlphaPixel/slughorn
cubicool · · focus · HN ↗