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

631–640 of 787 posts

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

#631

Post by emp17344 »

pertymcpert wrote: post #485
LinXitoW wrote: post #413

Earlier quoted context omitted.

Which is why we ought to always bring up their BS every time people try to pretend it didn't happen. The promises made are ABSOLUTELY relevant to how promising or not these experiments are.

I bet you get upset when you buy a new iPhone and don't love it, because Tim Cook said on the ad that they think you're going to love it.

It cannot be overstated how absurd the marketing campaign for AI was. OpenAI and Anthropic have convinced half the world that AI is going to become a literal god. They deserve to eat a lot of shit for those outright lies.

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

#632

Post by conception »

polyglotfacto wrote: post #627

So I do think one can get value from coding agents, but that value is out of proportion compared to the investments made by the AI labs, so now they're pushing this kind of stuff which I find to be a borderline scam. Let me explain why: > the resulting compiled output is over 60kb, far exceeding the 32k code limit enforced by Linux Seems like a failure to me. > I tried (hard!) to fix several of the above limitations…

I don’t understand. This badly done work wasn’t possible at all six months ago. In six more months it will be better. It’s not a mostly static technology for the last twenty plus years.

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

#633

Post by emp17344 »

sieep wrote: post #583
woeirua wrote: post #276

Earlier quoted context omitted.

We went from barely able to ask these things to write a function to writes a compiler that actually kind of works in under a year. But sure, keep moving the goal posts!

Didn't the Anthropic CEO claim we would be replaced by this AI tech by now? Here's Anthropic moving their own goal post in real time: 2026: https://www.entrepreneur.com/business-news/ai-ceo-says-softw... 2025: https://fortune.com/2025/03/13/ai-transforming-software-deve... https://www.entrepreneur.com/business-news/anthropic-ceo-pre...

Many people are convinced that we’re all going to die next year after these things achieve sentience. Can’t wait to see the goalpost shifting when AI 2027 doesn’t pan out.

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

#635

Post by Zambyte »

hex4def6 wrote: post #323
nmilo wrote: post #310

Earlier quoted context omitted.

What if you just read the entire GCC source code in school 15 years ago? Is that not clean room?

No. I'd argue that no one would really care given it's GCC. But if you worked for GiantSodaCo on their secret recipe under NDA, then create a new soda company 15 years later that tastes suspiciously similar to GiantSodaCo, you'd probably have legal issues. It would be hard to argue that you weren't using proprietary knowledge in that case.

Given that GCC is not public domain, the copyright holders will probably care.

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

#636

Post by vuciuc »

ajross wrote: post #617
pcloadlett3r wrote: post #417

Earlier quoted context omitted.

> it's probably good enough to use, yea. Not for general purpose use, only for demo. > that reasonably working software of equivalent complexity is within reach for $20k to solve But if this can't come close to replacing GCC and can't be modified without introducing bugs then it hasn't proven this yet. I learned some new hacks from the paper and that's great and all but from my experiencing of trying to harness even…

> Not for general purpose use, only for demo. What does that mean, though? I mean, it's already meeting a very high quality bar by booting at all and passing those tests. No, it doesn't beat existing solutions on all the checkboxes, but that's not what the demo is about. The point being demonstrated is that if you need a "custom compiler" or something similar for your own new, greenfield requirement , you can have it…

> you can have it at pretty-clearly-near-shippable quality in two weeks for $20k.

if you spend months writing a tight spec, tests and have a better version of the compiler around to use when everything else fails.

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

#637

Post by segh »

pcloadlett3r wrote: post #372
ajross wrote: post #311

Earlier quoted context omitted.

> $20,000 set on fire To be fair, that's two weeks of the employer cost of a FAANG engineer's labor. And no human hacks a working compiler in two weeks. It's a lot of AI compute for a demo, sure. But $20k stunts are hardly unique. Clearly there's value being demonstrated here.

Is there really value being presented here? Is this codebase a stable enough base to continue developing this compiler or does it warrant a total rewrite? Honest question, it seems like the author mentioned it being at its limits. This mirrors my own experience with Opus in that it isn't that great at defining abstractions in one-shot at least. Maybe with enough loops it could converge but I haven't seen definite pro…

This is an experiment to see the current limit of AI capabilities. The end result isn't useful, but the fact is established that in Feb 2026, you can spend $20k on AI to get a inefficient but working C complier.

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

#639

Post by gmueckl »

astrange wrote: post #536
gmueckl wrote: post #319

Earlier quoted context omitted.

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…

> The result is a fuzzy reproduction of the training input, specifically of the compilers contained within. Is it? I'm somewhat familiar with gcc and clang's source and it doesn't really particularly look like it to me. https://github.com/anthropics/claudes-c-compiler/blob/main/s... https://llvm.org/doxygen/LoopStrengthReduce_8cpp_source.html https://github.com/gcc-mirror/gcc/blob/master/gcc/gimple-ssa...

Checking for similarity with compilers that consist of orders of magnitudes more code probably doesn't reveal much. There many more smaller compilers for C-adjacent languages out there pkus cod3 fragments from text books.

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

#640

Post by gmueckl »

libraryofbabel wrote: post #342
gmueckl wrote: post #319

Earlier quoted context omitted.

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?

I personally work on simulation software and create novel simulation methods as part of the job. I find that LLMs can only help if I reduce that task to a translation of detailed algorithms descriptions from English to code. And even then, the output is often riddled with errors.
Post reply on HN