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

651–660 of 787 posts

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

#651

Post by spullara »

HarHarVeryFunny wrote: post #630
brundolf wrote: post #615

Earlier quoted context omitted.

One thing people have pointed out is that well-specified (even if huge and tedious) projects are an ideal fit for AI, because the loop can be fully closed and it can test and verify the artifact by itself with certainty. Someone was saying they had it generate a rudimentary JS engine because the available test suite is so comprehensive Not to invalidate this! But it's toward the "well-suited for AI" end of the spectr…

Yes - the gcc "torture test suite" that is mentioned must have been one of the enablers for this. It's notable that the article says Claude was unable to build a working assembler (& linker), which is nominally a much simpler task than building a compiler. I wonder if this was at least in part due to not having a test suite, although it seems one could be auto generated during bootstrapping with gas (GNU assembler) b…

i'm sure claude has been trained on every open source compiler

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

#652

Post by qarl »

rezonant wrote: post #555
qarl wrote: post #416

Earlier quoted context omitted.

[flagged]

I can't stress enough how much LOC is not a measure of anything .

OK, well, the people in MY software industry use LOC as an informal measure of complexity.

LIKE THE WHOLE WORLD DOES.

But hey, maybe it's just the extremely high profile projects I've worked on.

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

#653

Post by qarl »

beowulfey wrote: post #591
qarl wrote: post #416

Earlier quoted context omitted.

[flagged]

Your first post specifically stated: "I'm curious - do you have ANY idea what it costs to have humans write 100,000 lines of code???" which any reasonable reading would take to mean "paid-by-line", which we all know doesn't happen. Otherwise, I could type out 30,000 lines of gibberish and take my fat paycheck.

[flagged]

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

#654

Post by cma »

aurareturn wrote: post #592
byzantinegene wrote: post #514

Earlier quoted context omitted.

no, and that is widely known. the actual problem is that the margins are not sufficient at that scale to make up for the gargantuan training costs to train their SOTA model.

Source on that? Because inference revenue is outpacing training cost based on OpenAI’s report and intuition.

Net inference revenue would need to be outpacing to go against his think about margins.

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

#656

Post by cma »

vbezhenar wrote: post #437
icedchai wrote: post #394

Earlier quoted context omitted.

Yep. Building a working C compiler that compiles Linux is an impossible task for all but the top 1% of developers. And the ones that could do it have better things to do, plus they’d want a lot more than 20K for the trouble.

What's so hard about it? Compiler construction is well researched topic and taught in the universities. I made toy language compiler as a student. May be I'm underestimating this task, but I think that I can build some simple C compiler which will output trivial assembly. Given my salary of $2500, that would probably take me around a year, so that's pretty close LoL.

You can one shot prompt a toy C compiler. Getting one that can compile Linux in a bootable way is significantly harder.

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

#657

Post by a456463 »

hexo wrote: post #634

I really love how they waste energy for stuff like this. Even better, all that nonsense talk we constantly kept hearing about energy crysis just a few years ago...

Yup. All the tech hype bros are like "but my compiler"... Nobody was paying me to write a compiler, the meaning of "clean room" keeps changing, that they had to spend $20k (on the surface), not include the energy costs, the hardware costs, the time of assembly, etc. If you only paid that much money to a person and group of people. It is the hype bros wet dream to extract all value out of people and somehow get rich. Who cares if humanity suffers, look what I built for myself by enslaving people and wasting earth resources. Every single AI fetishist in this thread is responsible for it.

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

#658

Post by friendzis »

ryanjshaw wrote: post #620
PostOnce wrote: post #336

Earlier quoted context omitted.

It's amazing that it "works", but viability is another issue. It cost $20,000 and it worked, but it's also totally possible to spend $20,000 and have Claude shit out a pile of nonsense. You won't know until you've finished spending the money whether it will fail or not. Anthropic doesn't sell a contract that says "We'll only bill you if it works" like you can get from a bunch of humans. Do catastrophic bugs exist in…

> You won't know until you've finished spending the money whether it will fail or not. How do you conclude that? You start off with a bunch of tests and build these things incrementally, why would you spend 20k before realizing there’s a problem?

Because literally no real-world non-research project starts with "we have an extremely comprehensive test suite and specification complete down to the most finite detail" and then searches for a way to turn it into code.

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

#659

Post by a456463 »

ajross wrote: post #311
lubujackson wrote: post #265

This is very much a "vibe coding can build you the Great Pyramids but it can't build a cathedral" situation, as described earlier today: https://news.ycombinator.com/item?id=46898223 I know this is an impressive accomplishment and is meant to show us the future potential, but it achieves big results by throwing an insane amount of compute at the problem, brute forcing its way to functionality. $20,000 set on fire, at…

> $20,000 set on fire To be fair, that's two weeks of the employer cost of a FAANG engineer's labor. And no human hacks a working compiler in two weeks. It's a lot of AI compute for a demo, sure. But $20k stunts are hardly unique. Clearly there's value being demonstrated here.

Humans can hack a compiler in much less. Stop reading this hype and focus on learning

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

#660

Post by qarl »

m00x wrote: post #571
qarl wrote: post #369

Earlier quoted context omitted.

> It cost $20,000 I'm curious - do you have ANY idea what it costs to have humans write 100,000 lines of code??? You should look it up. :)

It really depends on the human and the code it outputs. I can get my 2y old child to output 100k LoC, but it won't be very good.

Your 2yr old can't build a C compiler in Rust that builds Linux.

Sorry mate, I think you're tripping.

Post reply on HN