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

We tasked Opus 4.6 using agent teams to build a C Compiler

anthropic.com

Post reply on HN
Print view View original

201–210 of 787 posts

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#201

Post by underdeserver »

phillmv wrote: post #190
ndesaulniers wrote: post #165

I spent a good part of my career (nearly a decade) at Google working on getting Clang to build the linux kernel. https://clangbuiltlinux.github.io/ This LLM did it in (checks notes): > Over nearly 2,000 Claude Code sessions and $20,000 in API costs It may build, but does it boot (was also a significant and distinct next milestone)? (Also, will it blend?). Looks like yes! > The 100,000-line compiler can build a bootab…

i mean… your work also went into the training set, so it's not entirely surprising that it spat a version back out!

Anthropic's version is in Rust though, so at least a little different.

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#203

Post by dyauspitr »

u8080 wrote: post #153
Retr0id wrote: post #146

Earlier quoted context omitted.

Can confirm (on aarch64 host) $ ./target/release/ccc-arm -I /usr/include/ -I /usr/local/include/ -I /usr/lib/gcc/aarch64-redhat-linux/15/include/ -o hello hello.c $ ./hello Hello from CCC!

Seems this non-artificial intelligence model just too limited to understand concept of include path.

It’s machine specific

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#204

Post by zaphirplane »

ndesaulniers wrote: post #165

I spent a good part of my career (nearly a decade) at Google working on getting Clang to build the linux kernel. https://clangbuiltlinux.github.io/ This LLM did it in (checks notes): > Over nearly 2,000 Claude Code sessions and $20,000 in API costs It may build, but does it boot (was also a significant and distinct next milestone)? (Also, will it blend?). Looks like yes! > The 100,000-line compiler can build a bootab…

What were the challenges out of interest. Some of it is the use of gcc extensions? Which needed an equivalent and porting over to the equivalent

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#205

Post by Rudybega »

falloutx wrote: post #197
Rudybega wrote: post #139

Earlier quoted context omitted.

It wrote the compiler in Rust. As far as I know, there aren't any Rust based C compilers with the same capabilities. If you can find one that can compile the Linux kernel or get 99% on the GCC torture test suite, I would be quite surprised. I couldn't in a search. Maybe read the article before being so dismissive.

Why does language of the compiler matter? Its a solved problem and since other implementations are already available anyone can already transpile them to rust.

Direct transpilation would create a ton of unsafe code (this repo doesn't have any) and fixing that would require a lot of manual fixes from the model. Even that would be a massive achievement, but it's not how this was created.

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#206

Post by underdeserver »

> when agents started to compile the Linux kernel, they got stuck. [...] Every agent would hit the same bug, fix that bug, and then overwrite each other's changes.

> [...] The fix was to use GCC as an online known-good compiler oracle to compare against. I wrote a new test harness that randomly compiled most of the kernel using GCC, and only the remaining files with Claude's C Compiler. If the kernel worked, then the problem wasn’t in Claude’s subset of the files. If it broke, then it could further refine by re-compiling some of these files with GCC. This let each agent work in parallel

This is a remarkably creative solution! Nicely done.

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#207

Post by ori_b »

ndesaulniers wrote: post #176
itay-maman wrote: post #168

My first reaction: wow, incredible. My second reaction: still incredible, but noting that a C compiler is one of the most rigorously specified pieces of software out there. The spec is precise, the expected behavior is well-defined, and test cases are unambiguous. I'm curious how well this translates to the kind of work most of us do day-to-day where requirements are fuzzy, many edge cases are discovered on the go, a…

> C compiler is one of the most rigorously specified pieces of software out there /me Laughs in "unspecified behavior."

There's undefined behavior, which is quite well specified. What do you mean by unspecified behavior? Do you have an example?

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#208

Post by chasd00 »

modeless wrote: post #31
NitpickLawyer wrote: post #19

This is a much more reasonable take than the cursor-browser thing. A few things that make it pretty impressive: > This was a clean-room implementation (Claude did not have internet access at any point during its development); it depends only on the Rust standard library. The 100,000-line compiler can build Linux 6.9 on x86, ARM, and RISC-V. It can also compile QEMU, FFmpeg, SQlite, postgres, redis > I started by draf…

There seem to still be a lot of people who look at results like this and evaluate them purely based on the current state. I don't know how you can look at this and not realize that it represents a huge improvement over just a few months ago, there have been continuous improvements for many years now, and there is no reason to believe progress is stopping here. If you project out just one year, even assuming progress…

i have to admit, even if model and tooling progress stopped dead today the world of software development has forever changed and will never go back.

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#209

Post by Cyphase »

nozzlegear wrote: post #192
NitpickLawyer wrote: post #142

Earlier quoted context omitted.

We've been hearing this for 3 years now. And especially 25 was full of "they've hit a wall, no more data, running out of data, plateau this, saturated that". And yet, here we are. Models keep on getting better, at more broad tasks, and more useful by the month.

> We've been hearing this for 3 years now Not from me you haven't! > "they've hit a wall, no more data, running out of data, plateau this, saturated that" Everyone thought Moore's Law was infallible too, right until they hit that bend. What hubris to think these AI models are different! But you've probably been hearing that for 3 years too (though not from me). > Models keep on getting better, at more broad tasks, an…

25 is 2025.

Re: We tasked Opus 4.6 using agent teams to build a C Compiler

#210

Post by cheema33 »

Havoc wrote: post #121

Cool project, but they really could have skipped the mention of clean room. Something trained on every copyrighted thing known to mankind is the opposite of clean room

As others have pointed out, humans train on existing codebases as well. And then use that knowledge to build clean room implementations.
Post reply on HN