This is a much more reasonable take than the cursor-browser thing. A few things that make it pretty impressive: > This was a clean-room implementation (Claude did not have internet access at any point during its development); it depends only on the Rust standard library. The 100,000-line compiler can build Linux 6.9 on x86, ARM, and RISC-V. It can also compile QEMU, FFmpeg, SQlite, postgres, redis > I started by draf…
There seem to still be a lot of people who look at results like this and evaluate them purely based on the current state. I don't know how you can look at this and not realize that it represents a huge improvement over just a few months ago, there have been continuous improvements for many years now, and there is no reason to believe progress is stopping here. If you project out just one year, even assuming progress…
We tasked Opus 4.6 using agent teams to build a C Compiler
131–140 of 787 posts
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#132Earlier quoted context omitted.
> This was a clean-room implementation This is really pushing it, considering it’s trained on… internet, with all available c compilers. The work is already impressive enough, no need for such misleading statements.
The LLM does not contain a verbatim copy of whatever it saw during the pre-training stage, it may remember certain over-represented parts, otherwise it has a knowledge about a lot of things but such knowledge, while about a huge amount of topics, is similar to the way you could remember things you know very well. And, indeed, if you give it access to internet or the source code of GCC and other compilers, it will imp…
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#133I am not using teams though and there is quite a bit of knowledge needed to direct it (even with the test suite).
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#134Earlier quoted context omitted.
We all saw verbatim copies in the early LLMs. They "fixed" it by implementing filters that trigger rewrites on blatant copyright infringement. It is a research topic for heaven's sake: https://arxiv.org/abs/2504.16046
The point is that it's a probabilistic knowledge manifold, not a database.
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#135At this point, I genuinely don't know what to learn next to not become obsolete when another Opus version gets released
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#136This is a much more reasonable take than the cursor-browser thing. A few things that make it pretty impressive: > This was a clean-room implementation (Claude did not have internet access at any point during its development); it depends only on the Rust standard library. The 100,000-line compiler can build Linux 6.9 on x86, ARM, and RISC-V. It can also compile QEMU, FFmpeg, SQlite, postgres, redis > I started by draf…
> This was a clean-room implementation This is really pushing it, considering it’s trained on… internet, with all available c compilers. The work is already impressive enough, no need for such misleading statements.
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#137Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#138https://github.com/anthropics/claudes-c-compiler/issues/1
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#139So it copied one of the C compilers? This was always possible but now you need to pay $1000 in API costs to Anthropic
Maybe read the article before being so dismissive.
Re: We tasked Opus 4.6 using agent teams to build a C Compiler
#140https://github.com/anthropics/claudes-c-compiler/issues/1