We tasked Opus 4.6 using agent teams to build a C Compiler • Hacker News Board

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

#341

Post by blibble » Fri, Feb 06, 2026, 12:59 AM UTC

simonw wrote: post #279

blibble wrote: post #266

Earlier quoted context omitted.

indeed building a working C compiler from scratch is literally in my "teach yourself C in 24 hours" book from 30 years ago

Which book was that? Sounds excellent. Might have been Compiler Design in C from 1990. Looks like that's available for free now: https://holub.com/compiler/

it's not that one, but it's in my parents house

you'll forgive me if I don't ring them in the early hours of the morning...

remember C was specifically designed to be easy to compile

(hence anachronisms like forward declarations)

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

#342

Post by libraryofbabel » Fri, Feb 06, 2026, 1:00 AM UTC

gmueckl wrote: post #319

libraryofbabel wrote: post #123

Earlier quoted context omitted.

Nobody disputes that the LLM was drawing on knowledge in its training data. Obviously it was! But you'll need to be a bit more specific with your critique, because there is a whole spectrum of interpretations, from "it just decompressed fuzzily-stored code verbatim from the internet" (obviously wrong, since the Rust-based C compiler it wrote doesn't exist on the internet) all the way to "it used general knowledge fro…

The result is a fuzzy reproduction of the training input, specifically of the compilers contained within. The reproduction in a different, yet still similar enough programming language does not refute that. The implementation was strongly guided by a compiler and a suite of tests as an explicit filter on those outputs and limiting the acceptable solution space, which excluded unwanted interpolations of the training s…

Thanks for elaborating. So what is the empirically-testable assertion behind this… that an LLM cannot create a (sufficiently complex) system without examples of the source code of similar systems in its training set? That seems empirically testable, although not for compilers without training a whole new model that excludes compiler source code from training. But what other kind of system would count for you?

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

#343

Post by nomel » Fri, Feb 06, 2026, 1:04 AM UTC

bhadass wrote: post #317

nomel wrote: post #298

Earlier quoted context omitted.

I would claim that LLMs desperately need proprietary code in their training, before we see any big gains in quality. There's some incredible source available code out there. Statistically, I think there's a LOT more not so great source available code out there, because the majority of output of seasoned/high skill developers is proprietary. To me, a surprising portion of Claude 4.5 output definitely looks like studen…

yeah, but isn't the whole point of claude code to get people to provide preference data/telemetry data to anthropic (unless you opt out?). same w/ other providers. i'm guessing most of the gains we've seen recently are post training rather than pretraining.

Yes, but you have the problem that a good portion of that is going to be AI generated.

But, I naively assume most orgs would opt out. I know some orgs have a proxy in place that will prevent certain proprietary code from passing through!

This makes me curious if, in the allow case, Anthropic is recording generated output, to maybe down-weight it if it's seen in the training data (or something similar)?

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

#344

Post by Crestwave » Fri, Feb 06, 2026, 1:04 AM UTC

bmandale wrote: post #230

hmry wrote: post #224

If I, a human, read the source code of $THING and then later implement my own version, that's not a "clean-room" re-implementation. The whole point of "clean-room" is that no single person has access to both the original code and the new code. (That way, you can legally prove that no copyright infringement took place.) But when an AI does it, now it counts? Opus is trained on the source code of Clang, GCC, TCC, etc.…

That's not the only way to protect yourself from accusations of copyright infringement. I remember reading that the GNU utils were designed to be as performant as possible in order to force themselves to structure the code differently from the unix originals.

Yes, but Anthropic is specifically claiming their implementation is clean-room, while GNU never made that claim AFAIK.

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

#345

Post by amlib » Fri, Feb 06, 2026, 1:13 AM UTC

minimaxir wrote: post #70

stonogo wrote: post #52

Earlier quoted context omitted.

AI companies set that expectation when their CEOs ran around telling anyone who would listen that their product is a generational paradigm shift that will completely restructure both labor markets and human cognition itself. There is no nuance in their own PR, so why should they benefit from any when their product can't meet those expectations?

Because it leads to poor and nonconstructive discourse that doesn't educate anyone about the implications of the tech, which is expected on social media but has annoyingly leaked to Hacker News. There's been more than enough drive-by comments from new accounts/green names even in this HN submission alone.

It's not just social media, it's IRL too.

Maybe the general population will be willing to have a more constructive discussions about this tech once the trillion dollar companies stop pillaging everything they see in front of them and cease acting like sociopaths whose only objectives seem to be concentrating power, generating dissidence and harvesting wealth.

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

#346

Post by tumdum_ » Fri, Feb 06, 2026, 1:15 AM UTC

PostOnce wrote: post #336

qarl wrote: post #332

Earlier quoted context omitted.

> Still a really cool project! Yeah. This test sorta definitely proves that AI is legit. Despite the millions of people still insisting it's a hoax. The fact that the optimizations aren't as good as the 40 year gcc project? Eh - I think people who focus on that are probably still in some serious denial.

It's amazing that it "works", but viability is another issue. It cost $20,000 and it worked, but it's also totally possible to spend $20,000 and have Claude shit out a pile of nonsense. You won't know until you've finished spending the money whether it will fail or not. Anthropic doesn't sell a contract that says "We'll only bill you if it works" like you can get from a bunch of humans. Do catastrophic bugs exist in…

> On top of that, Anthropic is losing money on it.

It seems they are *not* losing money on inference: https://bsky.app/profile/steveklabnik.com/post/3mdirf7tj5s2e

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

#347

Post by nmstoker » Fri, Feb 06, 2026, 1:18 AM UTC

wvenable wrote: post #324

jbjbjbjb wrote: post #286

Earlier quoted context omitted.

It’s cool but there’s a good chance it’s just copying someone else’s homework albeit in an elaborate round about way.

This is cool and actually demonstrates real utility. Using AI to take something that already exists and create it for a different library / framework / platform is cool. I'm sure there's a lot of training data in there for just this case. But I wonder how it would fare given a language specification for a non-existent non-trivial language and build a compiler for that instead?

If you come up with a realistic language spec and wait maybe six months, by then it'll probably be approach being cheap enough that you could test the scenario yourself!

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

#348

Post by bdangubic » Fri, Feb 06, 2026, 1:19 AM UTC

PostOnce wrote: post #336

qarl wrote: post #332

Earlier quoted context omitted.

> Still a really cool project! Yeah. This test sorta definitely proves that AI is legit. Despite the millions of people still insisting it's a hoax. The fact that the optimizations aren't as good as the 40 year gcc project? Eh - I think people who focus on that are probably still in some serious denial.

It's amazing that it "works", but viability is another issue. It cost $20,000 and it worked, but it's also totally possible to spend $20,000 and have Claude shit out a pile of nonsense. You won't know until you've finished spending the money whether it will fail or not. Anthropic doesn't sell a contract that says "We'll only bill you if it works" like you can get from a bunch of humans. Do catastrophic bugs exist in…

> On top of that, Anthropic is losing money on it

This has got to be my favorite one of them all that keeps coming up in too many comments… You know who also was losing money in the beginning?! every successful company that ever existed! some like Uber were losing billions for a decade. and when was the last time you rode in a taxi? (I still do, my kid never will). not sure how old you are and if you remember “facebook will never be able to monetize on mobile…” - they all lose money, until they do not

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

#349

Post by HarHarVeryFunny » Fri, Feb 06, 2026, 1:21 AM UTC

cheema33 wrote: post #210

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.

True, but the human isn't allowed to bring 1TB of compressed data pertaining to what they are "redesigning from scratch/memory" into the clean room.

In fact the idea of a "clean room" implementation is that all you have to go on is the interface spec of what you are trying to build a clean (non-copyright violating) version of - e.g. IBM PC BIOS API interface.

You can't have previously read the IBM PC BIOS source code, then claim to have created a "clean room" clone!

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

#350

Post by GorbachevyChase » Fri, Feb 06, 2026, 1:23 AM UTC

geraneum wrote: post #36

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…

> This was a clean-room implementation This is really pushing it, considering it’s trained on… internet, with all available c compilers. The work is already impressive enough, no need for such misleading statements.

https://arxiv.org/abs/2505.03335

Check out the paper above on Absolute Zero. Language models don’t just repeat code they’ve seen. They can learn to code give the right training environment.