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

351–360 of 787 posts

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

#351

Post by majormajor »

willsmith72 wrote: post #316
eek2121 wrote: post #307

Earlier quoted context omitted.

Also: a large amount of folks seem to think Claude code is losing a ton of money. I have no idea where the final numbers land, however, if the $20,000 figure is accurate and based on some of the estimates I've seen, they could've hired 8 senior level developers at a quarter million a year for the same amount of money spent internally. Granted, marketing sucks up far too much money for any startup, and again, we don't…

this doesn't add up. the 20k is in API costs. people talk about CC losing money because it's way more efficient than the API. I.e. the same work with efficient use of CC might have cost ~$5k. but regardless, hiring is difficult and high-end talent is limited. If the costs were anywhere close to equivalent, the agents are a no-brainer

CC hits their APIs, And internally I'm sure Anthropic tracks those calls, which is what they seem to be referencing here. What exactly did Anthropic do in this test to have "inefficient use of CC" vs your proposed "efficient use of CC"?

Or do you mean that if an external user replicated this experience they might get billed less than $20k due to CC being sold at lower rates than per-API-call metered billing?

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

#352

Post by the_jends »

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…

Being just a grunt engineer in a product firm I can't imagine being able to spend multiple years on one project. If it's something you're passionate about, that sounds like a dream!

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

#354

Post by jcranmer »

ndesaulniers wrote: post #232
underdeserver wrote: post #201

Earlier quoted context omitted.

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

There's parts of LLVM architecture that are long in the tooth (IMO) (as is the language it's implemented in, IMO). I had hoped one day to re-implement parts of LLVM itself in Rust; in particular, I've been curious if we can concurrently compile C (and parse C in parallel, or lazily) that haven't been explored in LLVM, and I think might be safer to do in Rust. I don't know enough about grammers to know if it's technic…

> I had hoped one day to re-implement parts of LLVM itself in Rust

Heh, earlier this day, I was just thinking how crazy a proposal would it actually be to have a Rust dependency (specifically, the egg crate, since one of the things I'm banging my head against right now might be better solved with egraphs).

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

#355

Post by kvemkon »

qarl wrote: post #332
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…

> 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.

> optimizations aren't as good as the 40 year gcc project

with all optimizations disabled:

> Even with all optimizations enabled, it outputs less efficient code than GCC with all optimizations disabled.

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

#356

Post by majormajor »

antirez wrote: post #88
geraneum wrote: post #36

Earlier quoted context omitted.

> 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.

The LLM does not contain a verbatim copy of whatever it saw during the pre-training stage, it may remember certain over-represented parts, otherwise it has a knowledge about a lot of things but such knowledge, while about a huge amount of topics, is similar to the way you could remember things you know very well. And, indeed, if you give it access to internet or the source code of GCC and other compilers, it will imp…

You couldn't reasonably claim you did a clean-room implementation of something you had read the source to even though you, too, would not have a verbatim copy of the entire source code in your memory (barring very rare people with exceptional memories).

It's kinda the whole point - you haven't read it so there's no doubt about copying in a clean-room experiment.

A "human style" clean-room copy here would have to be using a model trained on, say, all source code except GCC. Which would still probably work pretty well, IMO, since that's a pretty big universe still.

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

#357

Post by Calavar »

Aurornis wrote: post #262
philipportner wrote: post #175

Earlier quoted context omitted.

This seems related, it may not be a codebase but they are able to extract "near" verbatim books out of Claude Sonnet. https://arxiv.org/pdf/2601.02671 > For Claude 3.7 Sonnet, we were able to extract four whole books near-verbatim, including two books under copyright in the U.S.: Harry Potter and the Sorcerer’s Stone and 1984 (Section 4).

Their technique really stretched the definition of extracting text from the LLM. They used a lot of different techniques to prompt with actual text from the book, then asked the LLM to continue the sentences. I only skimmed the paper but it looks like there was a lot of iteration and repetitive trials. If the LLM successfully guessed words that followed their seed, they counted that as "extraction". They had to put i…

Sure, maybe it's tricky to coerce an LLM into spitting out a near verbatim copy of prior data, but that's orthoginal to whether or not the data to create a near verbatim copy exists in the model weights.

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

#358

Post by sdf2erf »

fmbb wrote: post #226
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.

> And yet, here we are. I dunno. To me it doesn’t even look exponential any more. We are at most on the straight part of the incline.

Personally my usage has fell off a cliff the past few months. Im not a SWE.

SWE's may be seeing benefit. But in other areas? Doesnt seem to be the case. Consumers may use it as a more preferred interface for search - but this is a different discussion.

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

#359

Post by bloaf »

eek2121 wrote: post #307
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…

Also: a large amount of folks seem to think Claude code is losing a ton of money. I have no idea where the final numbers land, however, if the $20,000 figure is accurate and based on some of the estimates I've seen, they could've hired 8 senior level developers at a quarter million a year for the same amount of money spent internally. Granted, marketing sucks up far too much money for any startup, and again, we don't…

This thing was done in 2 weeks. In the orgs I've worked in, you'd be lucky to get HR approval to create a job posting within 2 weeks.

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

#360

Post by eggn00dles »

HDThoreaun wrote: post #255
lossolo wrote: post #111

Earlier quoted context omitted.

Language doesn't really matter, it's not how things are mapped in the latent space. It only needs to know how to do it in one language.

Ok you can say this about literally any compiler though. The authors of every compiler have intimate knowledge of other compilers, how is this different?

grace hopper spinning in her grave rn
Post reply on HN