Ginux:以人類主導 AI 工程打造、可運行 Linux 用戶空間的新核心
Ginux: A New Kernel Runs Linux Userspace, Made via Human-Directed AI Engineering
Ginux 是一款以人類主導 AI 工程打造、可運行 Linux 用戶空間的新核心。Hacker News 討論者質疑這種工程方式是否有別於 vibecoding,並指出 AI 生成的程式碼仍須經過審核。
Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Ginux: A New Kernel Runs Linux Userspace, Made via Human-Directed AI Engineering (zenodo.org) 8 points by ForHackernews1 hour ago | hide | past | favorite | 11 comments help
codetiger2 minutes ago | next[–] I recently built a concept Linux OS with the entire UI generated by a local AI model based on the user's intend. https://github.com/codetiger/velliangiri reply
INTPenis35 minutes ago | prev | next[–] Why does it seem like HDAE is just a new term to distract from terms like "vibecoded" and "AI slop"? Because the bigger the project, the more unlikely it is for a human to review all the code. And in this case we're talking about re-making the Linux kernel. reply
pjmlp23 minutes ago | parent | next[–] Because it most certainly is. reply
palata22 minutes ago | parent | prev | next[–] My guess: - AI slop is clearly negative. "Lacking in effort", "low quality". - Vibecoding, I believe, tends to mean "letting the AI do it without putting much effort into it". So vibecoding produces AI slop. - HDAE, that this article tries to define, is "a method for building complex software by combining human-defined architecture, constraints, milestones, acceptance criteria, and stopping points with an autonomous implementation, execution, diagnosis, and revision loop". In other words, they say "it is actually possible to put a lot of effort into producing code with AI". And I personally don't disagree with that. Now of course, it feels like marketing, a bit. "I will present you how I built this kernel as an effort to make you accept it as "not slop", by trying to convince you that I put a lot of effort into producing it". IMO, it does not really matter. Whether code is written by a random person on the Internet, vibecoded by a random person on the Internet or HDAE-ed by a random person on the Internet, it should not be trusted unless audited. If it happens that vibecoded code is good, I don't see a reason not to use it. If HDAE-ed code is bad, it should not be used. reply
mschuster9114 minutes ago | root | parent | next[–] IME it is much, much more difficult to review code that is the result of a LLM regurgitation than to review human-written code made by someone even a bit experienced in programming - even more so if the human in question is a domain expert. For one, LLMs tend to waffle and produce code that works but is much more extensive and/or unintuitively organized than code that a human writes. The bigger thing however is testing. LLM code tends to test itself, whereas a domain expert human tends to have many more domain-specific edge cases in mind. reply
ithkuil18 minutes ago | parent | prev | next[–] Because we clearly need different terms to describe radically different processes that lead to different outcomes. reply
leothetechguy19 minutes ago | prev | next[–] I do not trust most research published on zenodo, in my experience almost everything there equates to AI Slop. reply
ahsg12323 minutes ago | prev | next[–] The new term for "stealing" is "Human-Directed Agentic Engineering". There are so many filthy people out there. reply
nign4 minutes ago | prev | next[–] Ever heard of gvisor...? reply
asmnzxklopqw16 minutes ago | prev | next[–] Let me help you here: you want to say “Made via AI slop”. reply
rvz16 minutes ago | prev[–] > "Made via Human-Directed AI Engineering" So vibe coded then. reply
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:
來源:Hacker News:AI 熱帖 · news.ycombinator.com