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

191–200 of 787 posts

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

#191

Post by ben_w »

philipportner wrote: post #178
ben_w wrote: post #106

Earlier quoted context omitted.

We saw partial copies of large or rare documents, and full copies of smaller widely-reproduced documents, not full copies of everything. An e.g. 1 trillion parameter model is not a lossless copy of a ten-petabyte slice of plain text from the internet. The distinction may not have mattered for copyright laws if things had gone down differently, but the gap between "blurry JPEG of the internet" and "learned stuff" is m…

Granted, these are some of the most widely spread texts, but just fyi: 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).

Already aware of that work, that's why I phrased it the way I did :)

Edit: actually, no, I take that back, that's just very similar to some other research I was familiar with.

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

#192

Post by nozzlegear »

NitpickLawyer wrote: post #142
nozzlegear wrote: post #131

Earlier quoted context omitted.

Every S-curve looks like an exponential until you hit the bend.

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, and more useful by the month.

If you say so, I'll take your word for it.

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

#193

Post by nozzlegear »

raincole wrote: post #148
nozzlegear wrote: post #131

Earlier quoted context omitted.

Every S-curve looks like an exponential until you hit the bend.

This quote would be more impactful if people haven't been repeating it since gpt-4 time.

I agree, I have been informed that people have been repeating it for three years. Sadly I'm not involved in the AI hype bubble so I wasn't aware. What an embarrassing faux pas.

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

#194

Post by dyauspitr »

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…

> Claude did not have internet access at any point during its development

Why is this even desirable? I want my LLM to take into account everything there is out there and give me the best possible output.

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

#195

Post by rwmj »

The interesting thing here is what's this code worth (in money terms)? I would say it's worth only the cost of recreation, apparently $20,000, and not very much more. Perhaps you can add a bit for the time taken to prompt it. Anyone who can afford that can use the same prompt to generate another C compiler, and another one and another one.

GCC and Clang are worth much much more because they are battle-tested compilers that we understand and know work, even in a multitude of corner cases, over decades.

In future there's going to be lots and lots of basically worthless code, generated and regenerated over and over again. What will distinguish code that provides value? It's going to be code - however it was created, could be AI or human - that has actually been used and maintained in production for a long time, with a community or company behind it, bugs being triaged and fixed and so on.

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

#196

Post by panzi »

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…

> clean-room implementation

Except its trained on all source out there, so I assume on GCC and clang. I wonder how similar the code is to either.

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

#197

Post by falloutx »

Rudybega wrote: post #139
falloutx wrote: post #24

So it copied one of the C compilers? This was always possible but now you need to pay $1000 in API costs to Anthropic

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.

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

#198

Post by IshKebab »

> I tried (hard!) to fix several of the above limitations but wasn’t fully successful. New features and bugfixes frequently broke existing functionality.

This has been my experience of vibe coding too. Good for getting started, but you quickly reach the point where fixing one thing breaks another and you have to finish the project yourself.

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

#199

Post by GaggiX »

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!

Clang is not written in Rust tho

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

#200

Post by shakna »

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…

> Opus was unable to implement a 16-bit x86 code generator needed to boot into 16-bit real mode. While the compiler can output correct 16-bit x86 via the 66/67 opcode prefixes, the resulting compiled output is over 60kb, far exceeding the 32k code limit enforced by Linux. Instead, Claude simply cheats here and calls out to GCC for this phase

Does it really boot...?

Post reply on HN