Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Learnings from 100K lines of Rust with AI (2025)

zfhuang99.github.io

Post reply on HN
Print view View original

41–50 of 225 posts

Re: Learnings from 100K lines of Rust with AI (2025)

#41

Post by boitiga »

embedding-shape wrote: post #32
boitiga wrote: post #30

Earlier quoted context omitted.

Honestly Rust is an UGLY language. For whatever powers it possesses in memory safety, its cryptic symbology is reminiscent of assembly. This is a problem when language designers are mathematicians and don’t understand typographical nuance and visual weights.

If I was forced to write it myself, then I'd agree, I'd use Clojure all day before Rust, because it's such a chore to write, edit and read. The whole "with AI" kind of reduces my hate for Rust though, and increases the appreciation for how strict the language is, especially when the agents themselves does the whole "do change > see error/warning > adjust code > re-check > repeat" loop themselves, which seems to work…

It’s funny I got downvoted immediately as expected.

I mean God help us should a crustacean try to understand the merits of my claim.

“Oh he’s saying something negative about rust…” Downvote!

I think with AI the language should still be readable. Humans need to be able to understand what’s going on!

Re: Learnings from 100K lines of Rust with AI (2025)

#42

Post by embedding-shape »

torben-friis wrote: post #4

>Testing is the first layer of defense. My system now includes 1,300+ tests — from unit tests to minimal integration tests (e.g., proposer + acceptor only), all the way to multi-replica full integration tests with injected failures. See the project status. I know LOC is a silly metric, but ~1300 tests for 130k lines averages out to a test per 100 lines - isn't this awfully low for a highly complex piece of code, even…

Considering the domain being distributed systems, and aiming to implement "a Rust-based multi-Paxos consensus engine that not only implements all the features of Azure’s Replicated State Library (RSL)", I don't think we even have to look so deep into it, it's severely lacking tests.

If you're building a distributed system and you don't have more tests and testing code than actual code, by an order of magnitude most likely, then you're missing test coverage.

Re: Learnings from 100K lines of Rust with AI (2025)

#43

Post by onlyrealcuzzo »

jdw64 wrote: post #9

I'm also shifting to an vibe coding workflow, but I have a genuine question: whenever I use AI for Rust, it makes an insane amount of lifetime errors. I have no idea how people are churning out so many lines of code so quickly. Honestly, despite all the hype around Rust in the community, the fact that AI can't handle lifetimes reliably makes me reluctant to use it. The AI constantly defaults to spamming .clone() or w…

> whenever I use AI for Rust, it makes an insane amount of lifetime errors.

What model are you using, and what frameworks are you using?

This is not a hard problem for LLMs to solve.

Rust is nearly the perfect language for LLMs.

It's exceptionally expressive, and it forbids entirely the most common globally complex bugs that LLMs simply do not (and won't for some time) have the context window size to properly reason about.

Dynamically typed languages are a disaster for LLMs because they allow global complexity WRT to implicit type contracts (that they do not and cannot be relied on to withhold).

If you're going to add types, as someone pointed out earlier, why are you even telling an LLM to write Python anyways?

Rust is barely harder to read than Python with types. It's highly expressive.

You have the `&mut` which seems alien, verbose (safe) concurrency, and lifetimes - which - if you're vibe coding... you don't really need to understand that thoroughly.

You want an LLM to write code in a language where "if it complies, it works" - because... let me tell you, if you vibe code in a language where errors are caught at runtime instead of compile time... It will definitely NOT work.

Re: Learnings from 100K lines of Rust with AI (2025)

#44

Post by mohsen1 »

embedding-shape wrote: post #37
mohsen1 wrote: post #33

Earlier quoted context omitted.

Lots and lots of guardrails to not allow slop. In tsz I have hard gates that disallow doing work in the wrong crate etc. https://github.com/mohsen1/tsz

> have hard gates that disallow doing work in the wrong crate Maybe I'm using agents wrong, but I'm not sure how you'd end up in that situation in the first place? When I start codex, codex literally only has access to the directory I'm launching it, with no way to navigate, read or edit stuff elsewhere on my disk, as it's wrapped in isolation with copied files into it, with no sync between the host. Hearing that oth…

tsz is an experiment in giving coding agents full control. On my day job I am a lot more careful. But I've moved on from manually approving every change and instead review the final diff. I noticed manually approving was counterproductive.

Re: Learnings from 100K lines of Rust with AI (2025)

#45

Post by arpinum »

nvader wrote: post #23
jdw64 wrote: post #9

I'm also shifting to an vibe coding workflow, but I have a genuine question: whenever I use AI for Rust, it makes an insane amount of lifetime errors. I have no idea how people are churning out so many lines of code so quickly. Honestly, despite all the hype around Rust in the community, the fact that AI can't handle lifetimes reliably makes me reluctant to use it. The AI constantly defaults to spamming .clone() or w…

I wrote and maintain this library of skills and workflows called Rust Bucket[0] It sets up your repo to ensure agents use a workflow which breaks your user requests down into separate beads, works on them serially, runs a judge agent after every bead is complete to apply code quality rules, and also strict static checks of your code. It's really helpful in extracting long, high-quality turns from the agent. It's what…

rust-bucket is 404, did you make it private?

Re: Learnings from 100K lines of Rust with AI (2025)

#46

Post by pelasaco »

embedding-shape wrote: post #32
boitiga wrote: post #30

Earlier quoted context omitted.

Honestly Rust is an UGLY language. For whatever powers it possesses in memory safety, its cryptic symbology is reminiscent of assembly. This is a problem when language designers are mathematicians and don’t understand typographical nuance and visual weights.

If I was forced to write it myself, then I'd agree, I'd use Clojure all day before Rust, because it's such a chore to write, edit and read. The whole "with AI" kind of reduces my hate for Rust though, and increases the appreciation for how strict the language is, especially when the agents themselves does the whole "do change > see error/warning > adjust code > re-check > repeat" loop themselves, which seems to work…

If I was forced to write it myself, i would love to keep writing ruby. What a wonderful language. I dont write ruby anymore, mostly using golang and python.. but ruby still a joy.

Re: Learnings from 100K lines of Rust with AI (2025)

#47

Post by criddell »

10g1k wrote: post #40

Lessons. There's no such thing as learnings.

Learnings is irritating to me. The way kids use the word aesthetic is irritating too. I wonder if I might be that old man shaking his fist at the clouds, but I have gotten over begs the question, and literally, so maybe not yet...

Re: Learnings from 100K lines of Rust with AI (2025)

#48

Post by mike_hearn »

onlyrealcuzzo wrote: post #43
jdw64 wrote: post #9

I'm also shifting to an vibe coding workflow, but I have a genuine question: whenever I use AI for Rust, it makes an insane amount of lifetime errors. I have no idea how people are churning out so many lines of code so quickly. Honestly, despite all the hype around Rust in the community, the fact that AI can't handle lifetimes reliably makes me reluctant to use it. The AI constantly defaults to spamming .clone() or w…

> whenever I use AI for Rust, it makes an insane amount of lifetime errors. What model are you using, and what frameworks are you using? This is not a hard problem for LLMs to solve. Rust is nearly the perfect language for LLMs. It's exceptionally expressive, and it forbids entirely the most common globally complex bugs that LLMs simply do not (and won't for some time) have the context window size to properly reason…

It's not nearly the perfect language for LLMs and Rust is dramatically harder to read and reason about than Python with types. Other options work better for nearly all apps. I found Kotlin works well:

- Garbage collected so no reasoning tokens or dev cycles are wasted on manual memory management. You say if you're vibe coding you can ignore lifetimes, but in response to a post that says AI can't do a good job and constantly uses escape hatches that lose the benefits of Rust (and can easily make it worse, copying data all over the place is terrible for performance).

- Very fast iteration speed due to JIT, a fast compiler and ability to use precompiled libraries. Rust is slow to compile.

- High level code that reads nearly like English.

- Semantically compatible with Java and Java libs, so lots of code in the training set.

- Unit tests are in separate files from sources. Rust intermixes them, bloating the context window with tests that may not be relevant to the current task.

Re: Learnings from 100K lines of Rust with AI (2025)

#49

Post by onlyrealcuzzo »

mike_hearn wrote: post #48
onlyrealcuzzo wrote: post #43

Earlier quoted context omitted.

> whenever I use AI for Rust, it makes an insane amount of lifetime errors. What model are you using, and what frameworks are you using? This is not a hard problem for LLMs to solve. Rust is nearly the perfect language for LLMs. It's exceptionally expressive, and it forbids entirely the most common globally complex bugs that LLMs simply do not (and won't for some time) have the context window size to properly reason…

It's not nearly the perfect language for LLMs and Rust is dramatically harder to read and reason about than Python with types. Other options work better for nearly all apps. I found Kotlin works well: - Garbage collected so no reasoning tokens or dev cycles are wasted on manual memory management. You say if you're vibe coding you can ignore lifetimes, but in response to a post that says AI can't do a good job and con…

Write a 250k LOC compiler in Python and then get back to me how well LLMs write in Python...

Sure if you want to vibe code a TODO app where it's literally just copying and pasting one it's already seen 10,000 times before, it can do it in Python.

Re: Learnings from 100K lines of Rust with AI (2025)

#50

Post by tskj »

10g1k wrote: post #40

Lessons. There's no such thing as learnings.

A lesson would be a specific learning activity happening at a specific place and time, administered by a person more knowledgeable than you; like a teacher or mentor "giving a lesson".

If you're fine with the generalized form "learned a lesson", then surely "learnings" is fine too. There's no point in trying to police a completely normal and sensible use of language.

Post reply on HN