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

241–250 of 787 posts

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

#241

Post by nozzlegear »

Cyphase wrote: post #209
nozzlegear wrote: post #192

Earlier quoted context omitted.

> We've been hearing this for 3 years now Not from me you haven't! > "they've hit a wall, no more data, running out of data, plateau this, saturated that" Everyone thought Moore's Law was infallible too, right until they hit that bend. What hubris to think these AI models are different! But you've probably been hearing that for 3 years too (though not from me). > Models keep on getting better, at more broad tasks, an…

25 is 2025.

Oh my bad, the way it was worded made me read it as the name of somebody's model or something.

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

#242

Post by mxey »

cheema33 wrote: post #210
Havoc wrote: post #121

Cool project, but they really could have skipped the mention of clean room. Something trained on every copyrighted thing known to mankind is the opposite of clean room

As others have pointed out, humans train on existing codebases as well. And then use that knowledge to build clean room implementations.

That’s the opposite of clean-room. The whole point of clean-room design is that you have your software written by people who have not looked into the competing, existing implementation, to prevent any claim of plagiarism.

“Typically, a clean-room design is done by having someone examine the system to be reimplemented and having this person write a specification. This specification is then reviewed by a lawyer to ensure that no copyrighted material is included. The specification is then implemented by a team with no connection to the original examiners.”

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

#243

Post by ndesaulniers »

bopbopbop7 wrote: post #228
beambot wrote: post #221

Earlier quoted context omitted.

This is getting close to a Ken Thompson "Trusting Trust" era -- AI could soon embed itself into the compilers themselves.

A pay to use non-deterministic compiler. Sounds amazing, you should start.

Some people care more about compile times than the performance of generated code. Perhaps even the correctness of generated code. Perhaps more so than determinism of the generated code. Different people in different contexts can have different priorities. Trying to make everyone happy can sometimes lead to making no one happy. Thus dichotomies like `-O2` vs `-Os`.

EDIT (since HN is preventing me from responding):

> Some people care more about compiler speed than the correctness?

Yeah, I think plenty of people writing code in languages that have concepts like Undefined Behavior technically don't really care as much about correctness as they may claim otherwise, as it's pretty hard to write large volumes of code without indirectly relying on UB somewhere. What is correct in such case was left up to interpretation of the implementer by ISO WG14.

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

#244

Post by nozzlegear »

torginus wrote: post #213
nozzlegear wrote: post #192

Earlier quoted context omitted.

> We've been hearing this for 3 years now Not from me you haven't! > "they've hit a wall, no more data, running out of data, plateau this, saturated that" Everyone thought Moore's Law was infallible too, right until they hit that bend. What hubris to think these AI models are different! But you've probably been hearing that for 3 years too (though not from me). > Models keep on getting better, at more broad tasks, an…

Except for Moore's law, everyone knew decades ahead of what the limits of Dennard scaling are (shrinking geometry through smaller optical feature sizes), and roughly when we would get to the limit. Since then, all improvements came at a tradeoff, and there was a definite flattening of progress.

> Since then, all improvements came at a tradeoff, and there was a definite flattening of progress.

Idk, that sounds remarkably similar to these AI models to me.

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

#246

Post by kingstnap »

rwmj wrote: post #195

The interesting thing here is what's this code worth (in money terms)? I would say it's worth only the cost of recreation, apparently $20,000, and not very much more. Perhaps you can add a bit for the time taken to prompt it. Anyone who can afford that can use the same prompt to generate another C compiler, and another one and another one. GCC and Clang are worth much much more because they are battle-tested compiler…

The code isn't worth money. This is an experiment. The knowledge that something like this is even possible is what is worth money.

If you had the knowledge that a transformer could pull this off in 2022. Even with all its flawed code. You would be floored.

Keep in mind that just a few years ago, the state of the art in what these LLMs could do was questions of this nature:

Suppose g(x) = f−1 (x), g(0) = 5, g(4) = 7, g(3) = 2, g(7) = 9, g(9) = 6 what is f(f(f(6)))?

The above is from the "sparks of AGI paper" on GPT-4, where they were floored that it could coherently reason through the 3 steps of inverting things (6 -> 9 -> 7 -> 4) while GPT 3.5 was still spitting out a nonsense argument of this form:

f(f(f(6))) = f(f(g(9))) = f(f(6)) = f(g(7)) = f(9).

This is from March 2023 and it was genuinely very surprising at the time that these pattern matching machines trained on next token prediction could do this. Something like a LSTM can't do anything like this at all btw, no where close.

To me its very surprising that the C compiler works. It takes a ton of effort to build such a thing. I can imagine the flaws actually do get better over the next year as we push the goalposts out.

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

#248

Post by hmry »

rishabhaiover wrote: post #233
hmry wrote: post #224

If I, a human, read the source code of $THING and then later implement my own version, that's not a "clean-room" re-implementation. The whole point of "clean-room" is that no single person has access to both the original code and the new code. (That way, you can legally prove that no copyright infringement took place.) But when an AI does it, now it counts? Opus is trained on the source code of Clang, GCC, TCC, etc.…

[flagged]

Just tired of AI companies having more rights than natural people when it comes to copyright infringement. Let us have some of the fun too!

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

#249

Post by irishcoffee »

ndesaulniers wrote: post #176
itay-maman wrote: post #168

My first reaction: wow, incredible. My second reaction: still incredible, but noting that a C compiler is one of the most rigorously specified pieces of software out there. The spec is precise, the expected behavior is well-defined, and test cases are unambiguous. I'm curious how well this translates to the kind of work most of us do day-to-day where requirements are fuzzy, many edge cases are discovered on the go, a…

> C compiler is one of the most rigorously specified pieces of software out there /me Laughs in "unspecified behavior."

Undefined is absolutely clear in the spec.

Unspecified is whatever you want it to mean. I am also laughing, having never heard "unspecified" before.

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

#250

Post by ndesaulniers »

beambot wrote: post #221
ndesaulniers wrote: post #165

I spent a good part of my career (nearly a decade) at Google working on getting Clang to build the linux kernel. https://clangbuiltlinux.github.io/ This LLM did it in (checks notes): > Over nearly 2,000 Claude Code sessions and $20,000 in API costs It may build, but does it boot (was also a significant and distinct next milestone)? (Also, will it blend?). Looks like yes! > The 100,000-line compiler can build a bootab…

This is getting close to a Ken Thompson "Trusting Trust" era -- AI could soon embed itself into the compilers themselves.

We're already starting to see people experimenting with applying AI towards register allocation and inlining heuristics. I think that many fields within a compiler are still ripe for experimentation.

https://llvm.org/docs/MLGO.html

Post reply on HN