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

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by gmueckl on Thursday February 05, 2026 @07:19PM (#46907377)

The result is a fuzzy reproduction of the training input, specifically of the compilers contained within. The reproduction in a different, yet still similar enough programming language does not refute that. The implementation was strongly guided by a compiler and a suite of tests as an explicit filter on those outputs and limiting the acceptable solution space, which excluded unwanted interpolations of the training set that also result from the lossy input compression.

The fact that the implementation language for the compiler is rust doesn't factor into this. ML based natural language translation has proven that model training produces an abstract space of concepts internally that maps from and to different languages on the input and output side. All this points to is that there are different implicitly formed decoders for the same compressed data embedded in the LLM and the keyword rust in the input activates one specific to that programming language.

[ Parent | on HN ]

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by libraryofbabel on Thursday February 05, 2026 @08:00PM (#46907664)

Thanks for elaborating. So what is the empirically-testable assertion behind this… that an LLM cannot create a (sufficiently complex) system without examples of the source code of similar systems in its training set? That seems empirically testable, although not for compilers without training a whole new model that excludes compiler source code from training. But what other kind of system would count for you?

[ Parent | on HN ]

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by gmueckl on Friday February 06, 2026 @10:52AM (#46914336)

I personally work on simulation software and create novel simulation methods as part of the job. I find that LLMs can only help if I reduce that task to a translation of detailed algorithms descriptions from English to code. And even then, the output is often riddled with errors.

[ Parent | on HN ]

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by astrange on Friday February 06, 2026 @05:00AM (#46910992)

> The result is a fuzzy reproduction of the training input, specifically of the compilers contained within.

Is it? I'm somewhat familiar with gcc and clang's source and it doesn't really particularly look like it to me.

https://github.com/anthropics/claudes-c-compiler/blob/main/s...

https://llvm.org/doxygen/LoopStrengthReduce_8cpp_source.html

https://github.com/gcc-mirror/gcc/blob/master/gcc/gimple-ssa...

[ Parent | on HN ]

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by gmueckl on Friday February 06, 2026 @10:49AM (#46914290)

Checking for similarity with compilers that consist of orders of magnitudes more code probably doesn't reveal much. There many more smaller compilers for C-adjacent languages out there pkus cod3 fragments from text books.

[ Parent | on HN ]

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by astrange on Friday February 06, 2026 @12:36PM (#46915746)

There are not many more compilers with the specific optimization pass I linked.

Also, I don't think you could reuse code from a different compiler unless you used the same IR.

[ Parent | on HN ]