跳到正文
Hacker News:AI 熱帖·· 2026-10-20AI 評分34

交付你的解譯器:以 Lean 驗證其編譯結果

Ship Your Interpreter

AI 導讀

這個方法先用 LLM 為小型程式語言撰寫精確的數學規則(形式語義),再以 Lean 證明解譯器編譯成 RISC-V 處理器可理解的低階指令後,仍符合這些規則。Hacker News 討論者批評文章的表達方式及 AI 寫作痕跡,也有人指出這種做法近似以既有解譯器作為規格。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Ship Your Interpreter (basis.ai) 21 points by gopiandcode6 hours ago | hide | past | favorite | 8 comments help Image 2ngruhn4 hours ago | next[–] This is great. Many people online who "verify their software" seem to just tell an LLM "verify dis" and have no idea what comes out. The model could be proving 1+1=2 for all they know. These guys actually show some Lean theorems they proved. Also interesting approach to compile the existing interpreter into the de-facto spec. reply Image 3jupitr1 hour ago | prev | next[–] This is the same idea as the fixed point of the meta-circular evaluator - the abstract ideal language that lisp models almost exactly. reply Image 4ISackKnights3 hours ago | prev | next[–] I am not sure what I have read here, I couldn't finish it, due to the AI writing. But you do have to wonder - Isn't this (just) a subset of Rust? reply Image 5imtringued3 hours ago | prev | next[–] This is AI slop. "Ship" in software means placing the interpreter into the release bundle, but here it is meant to refer to taking the interpreter as ground truth for formal verification (as opposed to a pristine spec), which sounds like incoherent AI writing. Usually metaphors are meant to make things easier to understand not harder. reply Image 6skavi5 hours ago | prev[–] > We had LLMs write precise mathematical rules, or a formal semantics, for how a small programming language should behave. We then used Lean, a tool for checking mathematical proofs, to prove that the interpreter—the program that runs code written in that language—follows those rules even after being compiled into low-level instructions understood by a RISC-V computer chip. who is your audience? why are you defining every single term here? perhaps i am less tenacious than most, but i wouldn't expect many who are unfamiliar with interpreters, formal proofs, or assembly language to be willing to charge on ahead—even when armed with that additional context. also, writing your very first paragraph via LLM is certainly a choice. reply Image 7artemonster4 hours ago | parent[–] I couldnt finish this slop. There is could be some value buried in there, but it could have been 10% of its size and human written reply Image 8trueno4 hours ago | root | parent[–] my brain ejects out of my skull when i see the EM dash. it's sort of insane to me people are willing to use LLM's to make stuff, but they can't even take the time to write why they think it's a valuable contribution. the shortcutting is off the charts, and this and a sea of other things shall go into the no thanks bin reply Image 9hnlmorg3 hours ago | root | parent[–] I agree with your general point but I really hate that the em dash has become so hated because it’s something I use commonly and have done before GPTs. Same goes for the Oxford comma too. reply Image 10 Consider applying for YC's Winter 2027 batch! Applications are open till November 2. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com