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

201–210 of 377 posts

Re: Claude’s C Compiler vs. GCC

#201

Post by 1718627440 »

simianwords wrote: post #145
nikitau wrote: post #107

Earlier quoted context omitted.

And not to mention that a C compiler is something we have literally 50 years worth of code for. I still seriously doubt the ability of LLMs to tackle truly new problems.

What do you classify as new? Every problem that we solve as developers is a very small deviation from already existing problems. Maybe that’s the point of llms? How many developers do you think are solving truly novel problems? Most like me are CRUD bunnies.

And these developers do not write the majority of their codebase, they use tons of libraries and only write the glue code.

Re: Claude’s C Compiler vs. GCC

#202

Post by agumonkey »

marcus_holmes wrote: post #8

I think this is a great example of both points of view in the ongoing debate. 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: Sure, but we can get the agent to fix that. Anti: Can you, though? We've seen that the more c…

This is a pattern I see a lot, in programming languages communities too, where it's a source a joy and dreams first and facts later.

Re: Claude’s C Compiler vs. GCC

#203

Post by VMG »

nvrmnd wrote: post #19
marcus_holmes wrote: post #8

I think this is a great example of both points of view in the ongoing debate. 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: Sure, but we can get the agent to fix that. Anti: Can you, though? We've seen that the more c…

> It's not fair to compare them like this! As someone who leans pro in this debate, I don't think I would make that statement. I would say the results are exactly as we expect. Also, a highly verifiable task like this is well suited to LLMs, and I expect within the next ~2 years AI tools will produce a better compiler than gcc.

> and I expect within the next ~2 years AI tools will produce a better compiler than gcc

and the "anti" crowd will point to some exotic architecture where it is worse

Re: Claude’s C Compiler vs. GCC

#204

Post by VMG »

red75prime wrote: post #195
marcus_holmes wrote: post #160

Earlier quoted context omitted.

Anthropic said they vibe-coded a C compiler that could compile the Linux kernel. That's what they said. No-one forced them to say that. They could have picked another code base. It turns out that isn't true in all instances, as this article demonstrates. I'm not nearly expert enough to be able to decide if that error was simple, stupid, irrelevant, or whatever. I can make a call on whether it successfully compiled th…

I'm sorry for being excessively edgy, but "it's useless" is not a good summary for "linking errors after successfully compiling Linux kernel for x86_64."

> Because if it’s worth your time to lie, it’s worth my time to correct it.

https://www.astralcodexten.com/p/if-its-worth-your-time-to-l...

Re: Claude’s C Compiler vs. GCC

#205

Post by enum »

Nice article. I believe the Claude C Compiler is an extraordinary research result.

The article is clear about its limitations. The code README opens by saying “don’t use this” which no research paper I know is honest enough to say.

As for hype, it’s less hyped than most university press releases. Of course since it’s Anthropic, it gets more attention than university press.

I think the people most excited are getting ahead of themselves. People who aren’t impressed should remember that there is no C compiler written in Rust for it to have memorized. But, this is going to open up a bunch of new and weird research directions like this blog post is beginning to do.

Re: Claude’s C Compiler vs. GCC

#206

Post by troupo »

onion2k wrote: post #114
codebolt wrote: post #112

Earlier quoted context omitted.

> People aren't prompting LLMs to write good, maintainable code though. Then they're not using the tools correctly. LLMs are capable of producing good clean code, but they need to be carefully instructed as to how. I recently used Gemini to build my first Android app, and I have zero experience with Kotlin or most of the libraries (but I have done many years of enterprise Java in my career). When I started I first ha…

When I started I first had a long discussion with the AI... and made a big Markdown file with a detailed architecture description. Yep, that's how you get better output from AI. A lot of devs haven't learned that yet. They still see it as 'better autocomplete'.

"It's just another Markdown file, bro".

LLMs do not learn. So every new session for them will be rebuilding the world from scratch. Bloated Markdown files quickly exhaust context windows, and agents routinely ignore large parts of them.

And then you unleash them on one code base that's more than a couple of days old, and they happily duplicate code, ignore existing code paths, ignore existing conventions etc.

Re: Claude’s C Compiler vs. GCC

#207

Post by enum »

wrxd wrote: post #92
o175 wrote: post #53

The 158,000x slowdown on SQLite is the number that matters here, not whether it can parse C correctly. Parsing is the solved problem — every CS undergrad writes a recursive descent parser. The interesting (and hard) parts of a compiler are register allocation, instruction selection, and optimization passes, and those are exactly where this falls apart. That said, I think the framing of "CCC vs GCC" is wrong. GCC has…

This thing has likely all of GCC, clang and any other open source C compiler in its training set. It could have spotted out GCC source code verbatim and matched its performance.

It’s in Rust…

Re: Claude’s C Compiler vs. GCC

#208

Post by troupo »

kleiba wrote: post #173
vasco wrote: post #125

Earlier quoted context omitted.

He is not polite, he is of the utmost rudeness. As a reply to being pointed to the fact that he copied so much code that the generated code included someone else's name in the License, his reply was https://github.com/ocaml/ocaml/pull/14369/changes/ce372a60bd... I struggle to think how someone thinks this is polite. Is politeness to you just not using curse words?

Admittedly, his handling of this aspect was perhaps less than ideal, but I cannot see any impoliteness here whatsoever. As a matter of fact, I struggle to think how you could think otherwise. But I am biased. After having lived a number of years in a country where I would say the average understanding of politeness is vastly different from where I've grown up, I've learned that there is just a difference of opinion o…

> but I cannot see any impoliteness here whatsoever.

Ah yes. "It's AI I don't care" and "AI has very deep reasoning about code, prove me wrong" are the height of politeness.

Re: Claude’s C Compiler vs. GCC

#209

Post by usrusr »

tossandthrow wrote: post #88
Alupis wrote: post #39

Earlier quoted context omitted.

I'm reminded, once again, of the recent "vibe coded" OCaml fiasco[1]. The PR author had zero understanding why their entirely LLM-generated contribution was viewed so suspiciously. The article validates a significant point: it is one thing to have passing tests and be able to produce output that resembles correctness - however it's something entirely different for that output to be good and maintainable . [1] https:/…

The Ai legal analysis seemed to be the nail in the coffin. Adding Ai generated comments are IMHO some of the most rude uses of Ai.

Not sure what exactly you're referring to, but legal is a very interesting field to observe, right? I've been wondering about that since quite early in my LLM awareness:

A slightly sarcastic (or perhaps not so slightly..) mental model of legal conflict resolution is that much of it boils down to throwing lots of content at the opposing side, claiming that it shows that the represented side is right and creating a task for the opposite side to find a flaw in that material. I believe that this game of quantity fits through the whole range from "I'll have my lawyer repeat my argument in a letter featuring their letter head" all the way to paper-tsunamis like the Google-Oracle trial.

Now give both sides access to LLM... I wonder if the legal profession will eventually settle on some format of in-person offline resolution with strict limits to recess and/or limits to word count for both documents and notes, because otherwise conflicts fail to get settled in anyone's lifetime (or won by whoever does not run out of tokens first - come thinking of it, the technogarchs would love this, so I guess this is exactly what will happen barring a revolution)

Re: Claude’s C Compiler vs. GCC

#210

Post by ncruces »

tossandthrow wrote: post #88
Alupis wrote: post #39

Earlier quoted context omitted.

I'm reminded, once again, of the recent "vibe coded" OCaml fiasco[1]. The PR author had zero understanding why their entirely LLM-generated contribution was viewed so suspiciously. The article validates a significant point: it is one thing to have passing tests and be able to produce output that resembles correctness - however it's something entirely different for that output to be good and maintainable . [1] https:/…

The Ai legal analysis seemed to be the nail in the coffin. Adding Ai generated comments are IMHO some of the most rude uses of Ai.

Some maintainers who drank the Kool-Aid, just use AI to answer to issues and review PRs.

Pretty soon we'll have AIs talking to each other.

Post reply on HN