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

151–160 of 787 posts

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

#151

Post by 0xCMP »

gmueckl wrote: post #44
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…

The result is hardly a clean room implementation. It was rather a brute force attempt to decompress fuzzily stored knowledge contained within the network and it required close steering (using a big suite of tests) to get a reasonable approximation to the desired output. The compression and storage happened during the LLM training. Prove this statement wrong.

I challenge anyone to try building a C compiler without a big suite of tests. Zig is the most recent attempt and they had an extensive test suite. I don't see how that is disqualifying.

If you're testing a model I think it's reasonable that "clean room" have an exception for the model itself. They kept it offline and gave it a sandbox to avoid letting it find the answers for itself.

Yes the compression and storage happened during the training. Before it still didn't work; now it does much better.

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

#152

Post by gmueckl »

Marha01 wrote: post #94
gmueckl wrote: post #44

Earlier quoted context omitted.

The result is hardly a clean room implementation. It was rather a brute force attempt to decompress fuzzily stored knowledge contained within the network and it required close steering (using a big suite of tests) to get a reasonable approximation to the desired output. The compression and storage happened during the LLM training. Prove this statement wrong.

Even with 1 TB of weights (probable size of the largest state of the art models), the network is far too small to contain any significant part of the internet as compressed data, unless you really stretch the definition of data compression.

This is obviously wrong. There is a bunch of knowledge embedded in those weights, and some of it can be recalled verbatim. So, by virtue of this recall alone, training is a form of lossy data compression.

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

#153

Post by u8080 »

Retr0id wrote: post #146
delusional wrote: post #143

Earlier quoted context omitted.

Naa, it looks like it's failing to include the standard system include directories. If you take then from gcc and pass them as -I, it'll compile.

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.

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

#155

Post by ben_w »

tza54j wrote: post #124
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…

We are here in a clean room implementation thread, and verbatim copies of entire works are irrelevant to that topic. It is enough to have read even parts of a work for something to be considered a derivative. I would also argue that language models who need gargantuan amounts of training material in order to work by definition can only output derivative works. It does not help that certain people in this thread (not…

> It is enough to have read even parts of a work for something to be considered a derivative.

For IP rights, I'll buy that. Not as important when the question is capabilities.

> I would also argue that language models who need gargantuan amounts of training material in order to work by definition can only output derivative works.

For similar reasons, I'm not going to argue against anyone saying that all machine learning today, doesn't count as "intelligent":

It is perfectly reasonable to define "intelligence" to be the inverse of how many examples are needed.

ML partially makes up for being (by this definition) thick as an algal bloom, by being stupid so fast it actually can read the whole internet.

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

#158

Post by geooff_ »

Maybe I'm naive, but I find these re-engineering complex product posts underwhelming. C Compilers exist and realistically Claudes training corpus contains a ton of C Compiler code. The task is already perfectly defined. There exists a benchmark of well-adopted codebases that can be used to prove if this is a working solution. Half the difficulty in making something is proving it works and is complete.

IMO a simpler novel product that humans enjoy is 10x more impressive than rehashing a solved problem, regardless of difficulty.

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

#159

Post by zamadatix »

delusional wrote: post #143
Retr0id wrote: post #138

Earlier quoted context omitted.

Looks like these users are just missing glibc-devel or equivalent?

Naa, it looks like it's failing to include the standard system include directories. If you take then from gcc and pass them as -I, it'll compile.

Hmm, I didn't have to do that. https://i.imgur.com/OAEtgvr.png

But yeah, either way it just needs to know where to find the stdlib.

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

#160

Post by Retr0id »

zamadatix wrote: post #159
delusional wrote: post #143

Earlier quoted context omitted.

Naa, it looks like it's failing to include the standard system include directories. If you take then from gcc and pass them as -I, it'll compile.

Hmm, I didn't have to do that. https://i.imgur.com/OAEtgvr.png But yeah, either way it just needs to know where to find the stdlib.

Probably depends on where your distro puts stuff by default, I think it has a few of the common include paths hardcoded.
Post reply on HN