Hacker News new | past | comments | ask | show | jobs | submit
rvz | on: Show HN: Kakehashi – Experimental userspace to run macOS binaries on Linux ARM
How can we tell that this is truly a clean room project and that there is no code from either (Claude or yourself) that is derived from the Darling project?

Otherwise great project.

vlad_kalinkin | parent | next
Thanks for the comment! You guessed it, I did use LLMs during development. While the strict definition of a "clean room" design can be debatable when AI is involved, I'd consider this a "light-gray room" approach. There is no direct code plagiarism here: Kakehashi is written from scratch in Rust, whereas Darling is built on C/objc. Furthermore, the architecture is fundamentally different—Darling relies on kernel-level emulation, while Kakehashi is purely focused on a lightweight userspace approach for Linux ARM. In my prompts, I explicitly restricted the use of proprietary components. Ultimately, the codebase speaks for itself, and I welcome everyone to audit the repository! Thanks again!
13rac1 | root | parent
FWIW Darling runs in userspace too.

What do you mean by "proprietary components"?

vlad_kalinkin | root | parent
Thanks! What I meant is that Kakehashi doesn't require a custom Linux kernel module (LKM). Kakehashi operates completely without root privileges or kernel-level modifications.

By "proprietary components," I meant that in my prompts, I explicitly forbade the copying or direct implementation of private Apple code. Of course, since LLMs are a bit of a black box, it's hard to be 100% certain about everything it synthesized under the hood, but the clear intent was to stick to public ABI definitions and standard open specs.

saurik | root | parent
Darling stopped using the kernel module a year ago.
billyjobob | parent
Darling is written in a different language so I don't think the LLM would copy paste code from it directly. But it is the main (only?) prior art, so it could be argued that everything the LLM knows about how to do this came because it read and understood Darling, i.e. if Darling didn't exist it may still be able to do this but it would have to figure it out from first principles.

Not saying it happened here, but it's an interesting thought experiment: what if you order an LLm to achieve the same goal as a popular open source project, using all the lessons learned and pitfalls faced by that project, but not to copy the code. Indeed, LLM code is now often better than human code, so direct code copying would be a disadvantage. Humans are certainly inspired by other projects like this all the time and it isn't considered plagiarism.

rvz | root | parent | next
> Darling is written in a different language so I don't think the LLM would copy paste code from it directly.

Just because it is written in a different language does not mean that it is a clean room implementation. The logic from Darling might as well have been lifted and then rewritten by a human or an LLM agent.

> Indeed, LLM code is now often better than human code, so direct code copying would be a disadvantage.

Is that why coding agents such as Claude Code and Codex have so many bugs in them? This is entirely dependent on the language chosen with the humans behind the decision to review and accept some of the changes.

> Humans are certainly inspired by other projects like this all the time and it isn't considered plagiarism.

Humans (researchers) also appropriately credit the work that inspires them, especially in experiments and research.

mathisfun123 | root | parent
you can copyright a specific implementation but that doesn't necessarily grant a patent on the "algorithm". so unless darling is patented then a translation of the "algorithms" in darling is legal. to wit: that's why all the "numerical recipes" books couldn't block implementations in other languages.
RossBencina | root | parent
IANAL and I don't think you are either. Be careful making simplistic inferences about a complicated system. Human "translation" is one thing, algorithmic "translation" has seen separate treatment in IP case law.[1] Whether this has relevance to LLM transformation or recall I don't know.

[1] https://en.wikipedia.org/wiki/Adobe_Systems,_Inc._v._Souther....

mathisfun123 | root | parent
Do you understand what you're saying?

> Human "translation" is one thing

No it's not since "human translation" is literally all we had until about a year ago.

You should read the case again because it doesn't say what you think it says - it says generating a copyrighted work via a new system is still infringement (which is exactly what I'm arguing isn't happening in this case because what's being generated is a new language impl).

To put it very simply: if I use a machine (biological or electrical) to translate my favorite song into another language that's not infringement.

nxc18 | root | parent
> Indeed, LLM code is now often better than human code

lol. Find better humans.

sterlind | root | parent
it depends on your prompting. LLMs can generate beautiful code, or absolute slop.