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

341–350 of 377 posts

Re: Claude’s C Compiler vs. GCC

#341

Post by AstroBen »

aurareturn wrote: post #258
techpression wrote: post #213

Earlier quoted context omitted.

Why would anything you learn today be relevant tomorrow if AI keeps advancing? You would need less and less of all your tooling, markdown files and other rituals and just let the AI figure it out altogether.

So I can keep my job now so I can pay for compute in the future when I'm out of a job. The compute will be used to create my own business to make money.

> The compute will be used to create my own business to make money

tell me you've never seriously attempted starting a software business without telling me

It's like all these people for the last 2 decades "if only I knew how to code I'd make an app and be rich!" yeah sure you would

Re: Claude’s C Compiler vs. GCC

#342

Post by charcircuit »

onion2k wrote: post #95
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:/…

however it's something entirely different for that output to be good and maintainable People aren't prompting LLMs to write good, maintainable code though. They're assuming that because we've made a collective assumption that good, maintainable code is the goal then it must also be the goal of an LLM too. That isn't true. LLMs don't care about our goals. They are solving problems in a probabilistic way based on the c…

>They are solving problems in a probabilistic way based on the content of their training data, context, and prompting.

>Presumably if you take all the code in the world and throw it in mixer what comes out is not our Platonic ideal of the best possible code, but actually something more like a Lovecraftian horror that happens to get the right output.

These statements are inaccurate since 2022 when LLMs started to have post training done.

Re: Claude’s C Compiler vs. GCC

#343

Post by bwfan123 »

direwolf20 wrote: post #250
bgirard wrote: post #150

Earlier quoted context omitted.

That's true and I fully agree. I don't think LLMs' progress in writing a toy C compiler diminishes the achievements that the GCC project did. But also we've just witnessed LLMs go from being a glorified line auto-complete tool to it writing a C compiler in ~3 years. And I think that's something. And noting how we keep moving the goal post.

GP: "it didn't write a C compiler, it copied other compilers. Writing one from scratch is a lot harder." You: "but look! It wrote a C compiler!"

The pattern matching rote-student is acing the class. No surprises here. There is no need to understand the subject from first principles to ace tests. Majority of high-school and college kids know this.

Re: Claude’s C Compiler vs. GCC

#344

Post by kleiba »

63stack wrote: post #327
kleiba wrote: post #93

Earlier quoted context omitted.

I just read that whole thread and I think the author made the mistake of submitting a 13k loc PR, but other than that - while he gets downvoted to hell on every comment - he's actually acting professionally and politely. I wouldn't call this a fiasco, it reads to me more that being able to create huge amounts of code - whether the end result works well or not - breaks the traditional model of open source. Small contr…

"Why did you submit these files that are attributed to a completely unrelated person?" "Beats me" Do you consider this "professional and polite"? Raise your standards.

Minimally, I don't find this an unusual tone in the slightest for cs threads. But then again, I'm old.

I'm also quite surprised that apparently you cannot utter what is clearly just a personal opinion -- not a claim of objective truth -- without getting downvoted. But then again, the semantics of votes are not well-defined.

At the same time, I'm quite grateful for the constructive comments further down below under my original post.

Re: Claude’s C Compiler vs. GCC

#345

Post by bwfan123 »

AstroBen wrote: post #338
codethief wrote: post #273

Earlier quoted context omitted.

> If you make the specs detailed enough so that there's no misunderstanding possible: you've just written code, what we already do today This was my opinion for a very long time. Having build a few applications from scratch using AI, though, nowadays I think: Sometimes not everything needs to be spelled out. Like in math papers some details can be left to the ~~reader~~LLM and it'll be fine. I mean, in many cases it…

Sometimes, yeah. I don't think we're disagreeing What I'd also add: Because of the unspecified behaviour, you're always going to need someone technical that understands the output to verify it. Tests aren't enough I'm not even sure if this is a net productivity benefit. I think it is? Some cases it's a clear win.. but definitely not always. You're reducing time coding and now putting extra into spec writing + review…

> Sometimes, yeah. I don't think we're disagreeing

I would disagree. Formalism and precision have a critical role to play which is often underestimated. More so with the advent of llms. Fuzziness of natural languages is both a strength and weakness. We have adopted precise but unnatural languages (math/C/C++) for describing machine models of the physical world or of the computing world. Such precision was a real human breakthrough which is often overlooked in these debates.

Re: Claude’s C Compiler vs. GCC

#346

Post by palmotea »

aurareturn wrote: post #334
palmotea wrote: post #330

Earlier quoted context omitted.

> What makes you think you’ll be able to out-compete the purely-AI-led businesses with your business? What skills will give you an edge in the business that won’t also give you an edge in the job? Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you? AI may just turn software into a pay to win game.

Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you? I don't know. Maybe because of my creativity? Anyways, I'm heavily invested in compute companies right now.

>> Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you?

> I don't know. Maybe because of my creativity?

How would you keep that up? I think there's a false belief, especially common in business-inflected spaces (which includes the tech sector), that skills and abilities can be endlessly specialized (e.g. the MBA claim that they're experts at running businesses, any business). The more you outsource to AI the less creative you'll become, because you'll lose touch with the work.

You can only really be creative in spaces where you regularly get your hands dirty. Lose that, and I think your "creativity" will become the equivalent of the MBA offering the same cookie-cutter financial engineering ideas to every business (layoffs, buy back stock, FOMO the latest faddish ideas, etc).

Re: Claude’s C Compiler vs. GCC

#347

Post by MrPowerGamerBR »

Alupis wrote: post #32
MrPowerGamerBR wrote: post #13

Earlier quoted context omitted.

In the original post Anthropic did point out that Claude Code did not have access to the internet

Presumably it had access to GCC (and LLVM/Clang) sources in it's training data? All of which are hosted or mirrored on Github.

I would've guess so, but I was talking about it in a "does Claude Code (not the model) have access to the internet?", which, according to Anthropic, it didn't.

Re: Claude’s C Compiler vs. GCC

#348

Post by nyantaro1 »

Culonavirus wrote: post #85
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:/…

Damn... "AI has a very deep understanding of how this code works. Please challenge me on this." this person is something else. Just... wow.

nice username

Re: Claude’s C Compiler vs. GCC

#349

Post by layer8 »

palmotea wrote: post #329
layer8 wrote: post #264

Earlier quoted context omitted.

It seems at least comparable to what you would have to pay a suitably competent developer to code up something similar.

> It seems at least comparable to what you would have to pay a suitably competent developer to code up something similar. No. You could have someone of fiverr do it for $5. Download gcc, done.

If only the Claude team knew that, they could have saved a lot of tokens.

Re: Claude’s C Compiler vs. GCC

#350

Post by pertymcpert »

mdavid626 wrote: post #230
pertymcpert wrote: post #193

Earlier quoted context omitted.

I have a feeling that you didn't because if you had, you'd realize it has more similarity to llvm than gcc.

Not sure who are you replying to. But me, personally, never said anything about gcc, nor llvm.

> I have a feeling, you didn't look at the code at all.

And you originally asked how someone knew that they weren't just spitting out gcc. So you reject their statement that it's not like gcc at all with your "you didn't look at the code at all". When its clear that you haven't looked at it.

Post reply on HN