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

Rust-lang/rust is adopting an LLM policy

blog.rust-lang.org

Post reply on HN
Print view View original

21–30 of 74 posts

Re: Rust-lang/rust is adopting an LLM policy

#21

Post by matheusmoreira »

duskdozer wrote: post #18
andsoitis wrote: post #2

In a nutshell: It's fine to use LLMs to answer questions, analyze, distill, refine, check, suggest, review. But not to create.

Creation is still allowed: >Pre-arranged, non-critical, high-quality, well-tested, and well-reviewed code changes that are originally created by an LLM are allowed, with disclosure.

It's technically an experiment, but it's definitely good to see they're keeping an open mind about this.

> Experiment: LLM-created code changes intended for review

> We leave space open to experiment with LLMs to inform future policies.

> This experiment is meant to inform future non-experimental policy, not to serve as the perpetual LLM usage policy.

Re: Rust-lang/rust is adopting an LLM policy

#22

Post by panstromek »

pas wrote: post #17
matheusmoreira wrote: post #15

The exact rules on LLM generated code submission live here: https://forge.rust-lang.org/policies/llm-usage.html https://rustc-dev-guide.rust-lang.org/llm-guidance/writing.h... > Pre-arranged, non-critical, high-quality, well-tested, and well-reviewed code changes that are originally created by an LLM are allowed, with disclosure. They clearly put a lot of thought into this and it shows. Huge respect. > New contributo…

> What is the correct procedure for this? in general to work on something that will get "into the rust compiler" it needs at least an RFC and then a Major Change Proposal [0] in practice it starts with asking on zulip [1] [0] https://forge.rust-lang.org/compiler/proposals-and-stabiliza... [1] https://forge.rust-lang.org/how-to-start-contributing.html

Asking on zulip is the good first step, yes. But RFC or MCP is only needed for bigger changes. Majority of changes will not need that, especially the ones contributed by newcomers.

Re: Rust-lang/rust is adopting an LLM policy

#23

Post by Cthulhu_ »

socalgal2 wrote: post #7
andsoitis wrote: post #2

In a nutshell: It's fine to use LLMs to answer questions, analyze, distill, refine, check, suggest, review. But not to create.

Sounds like the beginning of the end of rust to me AI is a jet engine - Banning is for creation is like saying "we require you to go by ship/car/propeller-plane" Yes, a policy that says AI slop PRs will not be tolerated. But I've had AI track down real hard to find bugs in several projects and provide correct fixes. I've also had AI build new features and new products. The project that ignores this acceleration will…

I love how your analogy actually works with the real world. You can't fly a jet plane until you've got all the various licenses and logged flying hours in prop planes first.

Re: Rust-lang/rust is adopting an LLM policy

#24

Post by Cthulhu_ »

imtringued wrote: post #13
socalgal2 wrote: post #7

Earlier quoted context omitted.

Sounds like the beginning of the end of rust to me AI is a jet engine - Banning is for creation is like saying "we require you to go by ship/car/propeller-plane" Yes, a policy that says AI slop PRs will not be tolerated. But I've had AI track down real hard to find bugs in several projects and provide correct fixes. I've also had AI build new features and new products. The project that ignores this acceleration will…

Why does a language need higher developer velocity? Why is acceleration needed? Acceleration makes sense for end user applications, where you're allowed to break whatever you see fit, but I don't see how it helps with core infrastructure like a programming language, where every mistake is multiplied a million fold.

Exactly this. There's plenty of boring software out there where writing the actual code is a chore. That's where AI works pretty well, as long as the people at the controls understand and can explain the problem and non-functionals.

For projects like Rust, coding velocity is not the bottleneck, speed / productivity is not a priority.

Re: Rust-lang/rust is adopting an LLM policy

#25

Post by matheusmoreira »

Cthulhu_ wrote: post #20
matheusmoreira wrote: post #15

The exact rules on LLM generated code submission live here: https://forge.rust-lang.org/policies/llm-usage.html https://rustc-dev-guide.rust-lang.org/llm-guidance/writing.h... > Pre-arranged, non-critical, high-quality, well-tested, and well-reviewed code changes that are originally created by an LLM are allowed, with disclosure. They clearly put a lot of thought into this and it shows. Huge respect. > New contributo…

> What is the correct procedure for this? Get involved with the project before submitting PRs, participate in discussions, etc. But if it's a change you want to contribute, don't use an LLM to write it.

> But if it's a change you want to contribute, don't use an LLM to write it.

The rules I quoted say LLM code generation is allowed should the developer contact a reviewer first and they agree to review it.

My question was about the exact procedure and etiquette for contacting these reviewers. For example, Linux has a get_maintainer.pl people can use to figure out who to email should they want to contribute something.

Re: Rust-lang/rust is adopting an LLM policy

#27

Post by zahlman »

incrudible wrote: post #8
seanhunter wrote: post #5

Earlier quoted context omitted.

Yes, and I think the reasons set out in TFA are interesting, which on my reading are: 1) Code is the least interesting bit in some ways - they’re trying to build not only rust but a community of experts around rust which is able to maintain and improve it in the long term and the authors of prs need to understand the code deeply and show a willingness to be part of that long run. Llm-generated code even if it looks p…

No codebase worth being deeply invested in is deeply understood by anyone, including the original authors. The eternal maintenance argument is tiresome. If there is a problem in need of fixing, you figure it out, you do not depend on some author being available, and LLMs are exceptionally helpful in this regard as well. Then, if the LLM has trouble figuring out, so will another human. It is a code smell.

There are all kinds of projects out there that have had significant impact on the world, which were written and maintained over the course of years by a single, highly capable developer. The way people talk about code nowadays, just because they have more powerful authoring tools, is frankly disgraceful. Imagine if modern construction techniques had become a reason to stop caring about the natural beauty of wood grain.

Re: Rust-lang/rust is adopting an LLM policy

#28

Post by duskdozer »

LoganDark wrote: post #9
feverzsj wrote: post #6

Earlier quoted context omitted.

You know rustaceans hate anything LLM when mods have to make this a rule.

It's not "rustaceans" as one whole. It's a very vocal minority (both rustacean and not) that make it everyone else's problem that they don't agree with the AI industry as a whole. I've had people try to convince me that I'm destroying the planet by using LLMs just because the process of creating the LLM was harmful to the climate. But that's like saying software piracy harms sales. Maybe the argument has more merit f…

If you can understand that some behavior is toxic and should be banned, then you should understand the people behind "cancel culture." Alternatively, if you see "cancelling" "cancel culture" as not "cancel culture", then you can understand the paradox of tolerance, and why an idealistic fully tolerant approach is not possible either way.

Re: Rust-lang/rust is adopting an LLM policy

#29

Post by matheusmoreira »

imtringued wrote: post #14
feverzsj wrote: post #6

Earlier quoted context omitted.

You know rustaceans hate anything LLM when mods have to make this a rule.

If you look at the Codeberg community, you'll find that this rule makes sense. The anti AI community is pretty toxic, probably more toxic than people throwing AI slop at reviewers.

Lobsters too.

Re: Rust-lang/rust is adopting an LLM policy

#30

Post by zahlman »

imtringued wrote: post #14
feverzsj wrote: post #6

Earlier quoted context omitted.

You know rustaceans hate anything LLM when mods have to make this a rule.

If you look at the Codeberg community, you'll find that this rule makes sense. The anti AI community is pretty toxic, probably more toxic than people throwing AI slop at reviewers.

In my experience, anti-AI coders are nowhere near as obnoxious (or even outright harmful) about it as their artist/graphic-designer counterparts.
Post reply on HN