Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude’s C Compiler vs. GCC

harshanu.space

Post reply on HN
Print view View original

301–310 of 377 posts

Re: Claude’s C Compiler vs. GCC

#301

Post by red75prime »

gjulianm wrote: post #253
red75prime wrote: post #62

Earlier quoted context omitted.

> Pro-LLM coding agents: look! a working compiler built in a few hours by an agent! this is amazing! > Anti-LLM coding agents: it's not a working compiler, though. And it doesn't matter how few hours it took, because it doesn't work. It's useless. Pro-LLM: Read the freaking article, it's not that long. The compiler made a mistake in an area where only two compilers exist that are up to the task: Linux Kernel.

> Read the freaking article The freaking article omits several issues in the "compiler". My bet is because they didn't actually challenged the output of the LLM, as it usually happens. If you go to the repository, you'll find fun things, like the fact that it cannot compile a bunch of popular projects, and that it compiles others but the code doesn't pass the tests. It's a bit surprising, specially when they don't ex…

The purpose of this project is not to create a state-of-the-art C compiler on par with projects that represent tens of thousands of developer-years. The goal is to assess the current capabilities of a largely autonomous software-building pipeline: it's not yet limitless, but better than it was. What a shocker.

I’ve had my share of build errors while compiling the Linux kernel for custom targets, so I wouldn’t be so sure that linker errors on x86_64 can’t be fixed with changes to the build script.

Re: Claude’s C Compiler vs. GCC

#302

Post by Aeglaecia »

kleiba wrote: post #294
Aeglaecia wrote: post #251

Earlier quoted context omitted.

interpreting his words on a literal basis , the PR submitter isn't being directly impolite ... if you will , place yourself in the shoes of the repository maintainer. a random person (with a personal agenda) has popped up trying to sell you a solution (that he doesn't understand) to a problem (that you don't see as problematic). after you spending literal hours patiently explaining why the proposition is not acceptab…

I think there's nothing wrong with trying to sell your solution, and I'm skeptical about the "literal hours" that you claim. The way I interpret this thread is that the PR poster had a certain itch and came up with a vibe-coded solution that helped him. Now he's trying to make that available for others too. The maintainers don't want it because it's too large a PR to review properly and because they don't want to hav…

that is indeed what is being argued , is it possible to screw someone over politely ?

Re: Claude’s C Compiler vs. GCC

#303

Post by vidarh »

antirez wrote: post #181

A few things to note: 1. In the real world, for a similar task, there are little reasons for: A) not giving the compiler access to all the papers about optimizations, ISAs PDFs, MIT-licensed compilers of all the kinds. It will perform much better, and this is a proof that the "uncompressing GCC" is just a claim (but even more point 2). 2. Of all the tasks, the assembler is the part where memorization would help the m…

> the experimenter was trying to show a different point of what the Internet got (as usually)

All of your points are important, but I think this is the most important one.

Having written compilers, $20k in tokens to get to a foundation for a new compiler with the feature set of this one is a bargain. Now, the $20k excludes the time of to set up the harness, so the total cost would be significantly higher, but still.

The big point here is that the researchers in question demonstrated that a complex task such as this could be achived shockingly cheaply, even when the agents were intentionally forced to work under unrealistically harsh conditions, with instructions to include features (e.g. SSA form) that significantly complicated the task but made the problem closer to producing the foundation for a "proper" compiler rather than a toy compiler, even if the outcome isn't a finished production-ready multi-arch C-compiler.

Re: Claude’s C Compiler vs. GCC

#304

Post by vidarh »

eb08a167 wrote: post #219
Ar-Curunir wrote: post #81

Earlier quoted context omitted.

If someone told you 5 years ago that a computer generated a working C compiler, would you think it was a big deal or not?

A computer generating a compiler is nothing new. Unzip has done this many many times. The key difference is that unzip extracts data from an archive in a deterministic way, while LLMs recover data from the training dataset using a lossy statistical model. Aid that with a feedback loop and a rich test suite, and you get exactly what Anthropic has achieved. While I agree that the technology behind this is impressive, t…

If you can show us code it has infringed on, you might have a point. Until then, you are making unfounded accusations.

Re: Claude’s C Compiler vs. GCC

#305

Post by vidarh »

chadcmulligan wrote: post #151
simianwords wrote: post #137

Earlier quoted context omitted.

It’s giving you an idea of what Claude is capable of - creating a project at the complexity of a small compiler. I don’t know if it can replace programmers but can definitely handle tasks of smaller complexity autonomously.

"autonomously" I couldn't agree with, I use it regularly for 100-200 loc size stuff, I can't recall it ever being right the first time.

I regularly has it produce 10k+ lines of code that is working and passing extensive test suites. If you give it a prompt and no agent loop and test harness, then sure, you'll need to waste your time babysitting it.

Re: Claude’s C Compiler vs. GCC

#306

Post by gordonhart »

kleiba wrote: post #292
vasco wrote: post #233

Earlier quoted context omitted.

You sound like you'd characterize a thief as polite if he asked you please when taking your wallet.

Ah, I see what you mean - you're making a distinction between someone's speech and someone's acts. Fair enough. In that sense, you would argue that the action of dropping a 13k loc PR is impolite, and I can see that. It's just that in my reading, I did not find his demeanor in the comment thread to be impolite. He was trying to sell his contribution and I think that whatever he wrote was using respectful language.

He responds to a thoughtful and detailed 600-word comment from a maintainer with a dismissive "Here's the AI-written copyright analysis..." + thousands of words of slop.

The effort asymmetry is what's rude. The maintainers take their project very seriously (as they should) and are generous enough with their time to invite contribution from outsiders. Showing up and dropping 13k lines of code, posting comments copy+pasted from a chat window, and insisting that your contribution is trustworthy not because you thought it through but because you fed it through a few LLMs shows that you don't respect the maintainers' time. In other words: you are being rude. They would have to put in more upfront effort to review your contribution than you put in to create it! Then they have to maintain it in perpetuity.

Re: Claude’s C Compiler vs. GCC

#307

Post by enum »

vidarh wrote: post #300
wrxd wrote: post #282

Earlier quoted context omitted.

It's an LLM, surely it could read gcc source code and translate it to Rust if it really tried hard enough

It wasn't given gcc source code, and was not given internet access. It the extent it could translate gcc source code, it'd need to be able to recall all of the gcc source from its weights.

Right. And the arguably simpler problem, where the model gets the C code directly, is active research: https://www.darpa.mil/research/programs/translating-all-c-to...

All of this work is extraordinarily impressive. It is hard to predict the impact of any single research project the week it is released. I doubt we'll ever throw away GCC/LLVM. But, I'd be surprised if the Claude C Compiler didn't have long-term impact on computing down the road.

Re: Claude’s C Compiler vs. GCC

#308

Post by co_king_3 »

monegator wrote: post #281
co_king_3 wrote: post #257

Earlier quoted context omitted.

[flagged]

*grifters

Successful grifters are not this stupid.

Terminal AI users are genuinely *slow* individuals.

These people are functionally illiterate; they are not able to extract information by reading a bit of text in the same ways that you or I are.

These people are very, very *gullible*.

Re: Claude’s C Compiler vs. GCC

#309

Post by tmtvl »

chvid wrote: post #57

What does the smallest (simplest in terms of complexity / lines of code) C-compiler that can compile and run SQLite look like? Perhaps that would be a more telling benchmark to evaluate the Claude compiler against.

I don't know for certain that it can compile and run SQLite, but the smallest C compiler I know of is SectorC: https://xorvoid.com/sectorc.html>

Re: Claude’s C Compiler vs. GCC

#310

Post by nhinck3 »

pertymcpert wrote: post #191
butipaidfor wrote: post #175

Earlier quoted context omitted.

But the poster, the ticket seller, and the ringmaster all said "Anna Pavlova reincarnated, a Bear that can dance as well as famous Ice Skaters!"

Who exactly said that? Can you give sources to high profile figures that said it?

Since we're in an Anthropic topic

https://www.businessinsider.com/anthropic-ceo-ai-90-percent-...

Post reply on HN