logoalt Hacker News

lambdaone • today at 11:54 AM • 7 replies • view on HN

Perhaps ironically, AI-based searching of the Rust compiler for bugs is likely to find more of these, pushing Rust closer and closer to the point of complete reliability.

The eventual formalization of Rust and a creation of a formally proven compiler is presumably going to be the end point of this process.


Replies

stingraycharles • today at 12:39 PM

Why would that be ironic? AI is helping us find so many subtle bugs and isolate the root cause, it’s nearly perfect for this type of use case.

groundzeros2015 • today at 2:08 PM

> complete reliability.

I think that’s a myth! What tends to happen in mature software is there are unfixable tradeoffs that can be made that favor one use case or another. And of course people will keep adding features too

mi_lk • today at 12:44 PM

What aspects of it are remotely ironic?

➕ show 2 replies
bbor • today at 12:02 PM

Until they find bugs in the formal proof program ;)

https://www.lesswrong.com/posts/zHhGa3iQBQcdSifFL/a-critical...

➕ show 2 replies
kimi • today at 12:15 PM

Or we realize that it is not possible, and Rust accepts to be "just" a definitely safer C.

➕ show 1 reply
malkia • today at 12:53 PM

and what stops AI from "accidentally" writing code with such bugs?

➕ show 1 reply
lifeisloving • today at 12:55 PM

I asked myself, How many comments to do I have to collapse before someone says something about AI. 3.

I used to compare this hype to crypto hype, but its so much worse. Can we just try not to shove llms into every single conversation.

Is there a hackernews type space where the word is banned? Even lobste.rs has this problem. I need some sort or way to just hide all content on certain sites where LLMs/AI are mentioned.

➕ show 1 reply