{"slug": "claude-s-c-compiler", "name": "Claude's C Compiler", "category": "dev-libs", "category_name": "Libraries and frameworks", "description": "", "recommenders": 3, "commenters": 21, "warners": 13, "score": -7.506, "rising": -0.98, "first": "2026-02-05", "latest": "2026-09-19", "why": "I'd be surprised if the Claude C Compiler didn't have long-term impact", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 4, "compare": 1, "warn": 14}, "spark": [0, 0, 0, 2, 1, 0, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I'd be surprised if the Claude C Compiler didn't have long-term impact", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/anthropics/claudes-c-compiler", "official_url": "https://github.com/anthropics/claudes-c-compiler", "pricing": "", "aliases": ["Claude's C Compiler", "claudes-c-compiler", "Claude C Compiler", "Claude's C compiler", "Claude C compiler"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 756731889, "item_id": 47295743, "url": "https://news.ycombinator.com/item?id=47295743", "by": "networked", "date": "2026-03-08", "version": null, "stance": "recommend", "quote": "The compiler works:", "excerpt": "Strange subthread. I don't see Claude Opus 4.6 changing the tide for PyPy. There is no need to understate AI capabilities for this. \"Anthropic released vibe coded C compiler that doesn't work\" sounds like https://github.com/anthropics/claudes-c-compiler/issues/1 passed through a game of telephone. The compiler has some wrong defaults that prevent it from straightforwardly building a \"Hello, world!\" like GCC and Clang", "context": "", "use_case": "C compiler built by Claude", "switched_from": "", "story": "\"Warn about PyPy being unmaintained\""}, {"id": 752187408, "item_id": 47011713, "url": "https://news.ycombinator.com/item?id=47011713", "by": "NewsaHackO", "date": "2026-02-13", "version": null, "stance": "recommend", "quote": "I am not seeing how this shows that CCC is not impressive", "excerpt": ">I found this was the least impressive bit about it https://github.com/anthropics/claudes-c-compiler/issues/1 So, I just skimmed the discussion thread, but I am not seeing how this shows that CCC is not impressive. Is the point you're making that the person who opened the issue is not impressive?", "context": "", "use_case": "", "switched_from": "", "story": "GPT-5.2 derives a new result in theoretical physics"}, {"id": 751120528, "item_id": 46945033, "url": "https://news.ycombinator.com/item?id=46945033", "by": "enum", "date": "2026-02-09", "version": null, "stance": "recommend", "quote": "I'd be surprised if the Claude C Compiler didn't have long-term impact", "excerpt": "Right. And the arguably simpler problem, where the model gets the C code directly, is active research: https://www.darpa.mil/research/programs/translating-all-c-to-rust All of this work is extraordinarily impressive. It is hard to predict the impact of any single research project the week it is released. I doubt we'll ever throw away GCC/LLVM. But, I'd be surprised if the Claude C Compiler didn't have long-term impac", "context": "", "use_case": "", "switched_from": "", "story": "Claude's C Compiler vs. GCC"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 781675712, "item_id": 48854732, "url": "https://news.ycombinator.com/item?id=48854732", "by": "rvz", "date": "2026-07-09", "version": null, "stance": "warn", "quote": "How is that going for Claude's C compiler [0], or Cursor's web browser? [1]", "excerpt": "How is that going for Claude's C compiler [0], or Cursor's web browser? [1] [0] https://github.com/anthropics/claudes-c-compiler [1] https://github.com/wilsonzlin/fastrender", "context": "", "use_case": "", "switched_from": "", "story": "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"}, {"id": 777552929, "item_id": 48597058, "url": "https://news.ycombinator.com/item?id=48597058", "by": "dminik", "date": "2026-06-19", "version": null, "stance": "warn", "quote": "The Claude C compiler? 4 months since any changes", "excerpt": "Ah, that reminded me to check up on these \"AI wonder projects\". Cursor's Web Browser? Last update 5 months ago: https://github.com/wilsonzlin/fastrender The Claude C compiler? 4 months since any changes: https://github.com/anthropics/claudes-c-compiler Zero moderation too, nice. https://github.com/anthropics/claudes-c-compiler/issues/264#issuecomment-4323295564 CloudFlare's slop NextJS project is still going though. ", "context": "", "use_case": "", "switched_from": "", "story": "Fable Converted Pylint to Rust"}, {"id": 775705904, "item_id": 48481619, "url": "https://news.ycombinator.com/item?id=48481619", "by": "rvz", "date": "2026-06-10", "version": null, "stance": "warn", "quote": "When was the last time Claude's C Compiler was updated? 4 months ago?", "excerpt": "When was the last time Claude's C Compiler was updated? 4 months ago? [0] It is written in Rust\u2122, surely it is better than the rest of them. [0] https://github.com/anthropics/claudes-c-compiler", "context": "", "use_case": "", "switched_from": "", "story": "Claude Desktop spins up a VM without no way of stopping it"}, {"id": 775639136, "item_id": 48477446, "url": "https://news.ycombinator.com/item?id=48477446", "by": "bwfan123", "date": "2026-06-10", "version": null, "stance": "warn", "quote": "what happened to that after the initial press releases", "excerpt": "Part of the problem is that of human alienation. By excluding humans in the construction process, it has taken away any skin-in-the-game for humans. So, there could be a point where some bugs become unresolvable because LLMs dont have an adequate causal model and fixes by trial-and-error wont work in cases where root-causes are not properly addressed - and the project gets abandoned as a result. Witness the C compile", "context": "", "use_case": "", "switched_from": "", "story": "Port React Compiler to Rust"}]}], "who": [], "tags": [], "use_cases": ["c compiler built by claude", "c compiler", "compiling linux kernel"], "compared": [{"slug": "gcc", "name": "GCC", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46903616", "title": "We tasked Opus 4.6 using agent teams to build a C Compiler", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=46941603", "title": "Claude's C Compiler vs. GCC", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=47006594", "title": "GPT-5.2 derives a new result in theoretical physics", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49763928", "title": "If math is more than proof, we need to better celebrate the rest of it", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48841676", "title": "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48594733", "title": "Fable Converted Pylint to Rust", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"warn": 8, "neutral": 2, "compare": 1, "recommend": 2}, "2026-03": {"neutral": 1, "warn": 1, "recommend": 1}, "2026-04": {}, "2026-05": {"warn": 1}, "2026-06": {"warn": 3}, "2026-07": {"warn": 1}, "2026-08": {}, "2026-09": {"neutral": 1}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 796250032, "item_id": 49765627, "url": "https://news.ycombinator.com/item?id=49765627", "by": "mathisfun123", "date": "2026-09-19", "version": null, "stance": "neutral", "quote": "You missed this from last year", "excerpt": "You missed this from last year https://github.com/anthropics/claudes-c-compiler Also I dunno why you should be impressed by this - gcc isn't anything near eg navier stokes", "context": "", "use_case": "", "switched_from": "", "story": "If math is more than proof, we need to better celebrate the rest of it"}, {"id": 781675712, "item_id": 48854732, "url": "https://news.ycombinator.com/item?id=48854732", "by": "rvz", "date": "2026-07-09", "version": null, "stance": "warn", "quote": "How is that going for Claude's C compiler [0], or Cursor's web browser? [1]", "excerpt": "How is that going for Claude's C compiler [0], or Cursor's web browser? [1] [0] https://github.com/anthropics/claudes-c-compiler [1] https://github.com/wilsonzlin/fastrender", "context": "", "use_case": "", "switched_from": "", "story": "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"}, {"id": 777552929, "item_id": 48597058, "url": "https://news.ycombinator.com/item?id=48597058", "by": "dminik", "date": "2026-06-19", "version": null, "stance": "warn", "quote": "The Claude C compiler? 4 months since any changes", "excerpt": "Ah, that reminded me to check up on these \"AI wonder projects\". Cursor's Web Browser? Last update 5 months ago: https://github.com/wilsonzlin/fastrender The Claude C compiler? 4 months since any changes: https://github.com/anthropics/claudes-c-compiler Zero moderation too, nice. https://github.com/anthropics/claudes-c-compiler/issues/264#issuecomment-4323295564 CloudFlare's slop NextJS project is still going though. ", "context": "", "use_case": "", "switched_from": "", "story": "Fable Converted Pylint to Rust"}, {"id": 775705904, "item_id": 48481619, "url": "https://news.ycombinator.com/item?id=48481619", "by": "rvz", "date": "2026-06-10", "version": null, "stance": "warn", "quote": "When was the last time Claude's C Compiler was updated? 4 months ago?", "excerpt": "When was the last time Claude's C Compiler was updated? 4 months ago? [0] It is written in Rust\u2122, surely it is better than the rest of them. [0] https://github.com/anthropics/claudes-c-compiler", "context": "", "use_case": "", "switched_from": "", "story": "Claude Desktop spins up a VM without no way of stopping it"}, {"id": 775639136, "item_id": 48477446, "url": "https://news.ycombinator.com/item?id=48477446", "by": "bwfan123", "date": "2026-06-10", "version": null, "stance": "warn", "quote": "what happened to that after the initial press releases", "excerpt": "Part of the problem is that of human alienation. By excluding humans in the construction process, it has taken away any skin-in-the-game for humans. So, there could be a point where some bugs become unresolvable because LLMs dont have an adequate causal model and fixes by trial-and-error wont work in cases where root-causes are not properly addressed - and the project gets abandoned as a result. Witness the C compile", "context": "", "use_case": "", "switched_from": "", "story": "Port React Compiler to Rust"}, {"id": 770750048, "item_id": 48171878, "url": "https://news.ycombinator.com/item?id=48171878", "by": "nvme0n1p1", "date": "2026-05-17", "version": null, "stance": "warn", "quote": "Apparently compiling hello world exactly as the README says to is an unfair expectation of the software.", "excerpt": "Why are you quoting from their marketing blog as if it's a reliable source? https://github.com/anthropics/claudes-c-compiler/issues/1 > Apparently compiling hello world exactly as the README says to is an unfair expectation of the software.", "context": "", "use_case": "", "switched_from": "", "story": "I don't think AI will make your processes go faster"}, {"id": 756731889, "item_id": 47295743, "url": "https://news.ycombinator.com/item?id=47295743", "by": "networked", "date": "2026-03-08", "version": null, "stance": "recommend", "quote": "The compiler works:", "excerpt": "Strange subthread. I don't see Claude Opus 4.6 changing the tide for PyPy. There is no need to understate AI capabilities for this. \"Anthropic released vibe coded C compiler that doesn't work\" sounds like https://github.com/anthropics/claudes-c-compiler/issues/1 passed through a game of telephone. The compiler has some wrong defaults that prevent it from straightforwardly building a \"Hello, world!\" like GCC and Clang", "context": "", "use_case": "C compiler built by Claude", "switched_from": "", "story": "\"Warn about PyPy being unmaintained\""}, {"id": 755941680, "item_id": 47246355, "url": "https://news.ycombinator.com/item?id=47246355", "by": "maccard", "date": "2026-03-04", "version": null, "stance": "warn", "quote": "You mean the C compiler that literally failed to compile a hello world", "excerpt": "> At this point though, after Claude C Compiler, Perfect example. You mean the C compiler that literally failed to compile a hello world [0] (which was given in it's readme)? > What do you consider simple issues? Hallucinating APIs for well documented libraries/interfaces, ignoring explicit instructions for how to do things, and making very simple logic errors in 30-100 line scripts. As an example, I asked Claude cod", "context": "", "use_case": "", "switched_from": "", "story": "Agentic Engineering Patterns"}, {"id": 755859104, "item_id": 47241194, "url": "https://news.ycombinator.com/item?id=47241194", "by": "faitswulff", "date": "2026-03-03", "version": null, "stance": "neutral", "quote": "Someone actually did fuzz the claude c compiler:", "excerpt": "Someone actually did fuzz the claude c compiler: https://john.regehr.org/writing/claude_c_compiler.html", "context": "", "use_case": "", "switched_from": "", "story": "When AI Writes the Software, Who Verifies It?"}, {"id": 752187408, "item_id": 47011713, "url": "https://news.ycombinator.com/item?id=47011713", "by": "NewsaHackO", "date": "2026-02-13", "version": null, "stance": "recommend", "quote": "I am not seeing how this shows that CCC is not impressive", "excerpt": ">I found this was the least impressive bit about it https://github.com/anthropics/claudes-c-compiler/issues/1 So, I just skimmed the discussion thread, but I am not seeing how this shows that CCC is not impressive. Is the point you're making that the person who opened the issue is not impressive?", "context": "", "use_case": "", "switched_from": "", "story": "GPT-5.2 derives a new result in theoretical physics"}, {"id": 752156544, "item_id": 47009784, "url": "https://news.ycombinator.com/item?id=47009784", "by": "kewscombinator", "date": "2026-02-13", "version": null, "stance": "warn", "quote": "I found this was the least impressive bit about it", "excerpt": "I found this was the least impressive bit about it https://github.com/anthropics/claudes-c-compiler/issues/1", "context": "", "use_case": "", "switched_from": "", "story": "GPT-5.2 derives a new result in theoretical physics"}, {"id": 752135808, "item_id": 47008488, "url": "https://news.ycombinator.com/item?id=47008488", "by": "BrouteMinou", "date": "2026-02-13", "version": null, "stance": "warn", "quote": "Deliver what exactly? False hope and lies?", "excerpt": "Deliver what exactly? False hope and lies? https://github.com/anthropics/claudes-c-compiler/issues/228", "context": "", "use_case": "C compiler", "switched_from": "", "story": "GPT-5.2 derives a new result in theoretical physics"}, {"id": 751137808, "item_id": 46946113, "url": "https://news.ycombinator.com/item?id=46946113", "by": "gjulianm", "date": "2026-02-09", "version": null, "stance": "warn", "quote": "Considering that it's full of bugs and incomplete implementations and cannot be changed without things breaking down", "excerpt": "> The goal is to assess the current capabilities of a largely autonomous software-building pipeline: it's not yet limitless, but better than it was. What a shocker. Of course, but we're trying to assess the capabilities by looking at the LLM output as if it were a program written by a person. If someone told me to check out their new C compiler that can build the kernel, I'd assume that other basic things, such as no", "context": "", "use_case": "", "switched_from": "", "story": "Claude's C Compiler vs. GCC"}, {"id": 751120528, "item_id": 46945033, "url": "https://news.ycombinator.com/item?id=46945033", "by": "enum", "date": "2026-02-09", "version": null, "stance": "recommend", "quote": "I'd be surprised if the Claude C Compiler didn't have long-term impact", "excerpt": "Right. And the arguably simpler problem, where the model gets the C code directly, is active research: https://www.darpa.mil/research/programs/translating-all-c-to-rust All of this work is extraordinarily impressive. It is hard to predict the impact of any single research project the week it is released. I doubt we'll ever throw away GCC/LLVM. But, I'd be surprised if the Claude C Compiler didn't have long-term impac", "context": "", "use_case": "", "switched_from": "", "story": "Claude's C Compiler vs. GCC"}, {"id": 751108928, "item_id": 46944308, "url": "https://news.ycombinator.com/item?id=46944308", "by": "gjulianm", "date": "2026-02-09", "version": null, "stance": "warn", "quote": "Several people have pointed out that the compiler will not emit errors for clearly invalid code.", "excerpt": "> This was the equivalent of a \"weekend project\", and it's amazing > Building a C compiler which can correctly compile (maybe not link) the modern linux kernel is damn hard. Is it correctly compiling it? Several people have pointed out that the compiler will not emit errors for clearly invalid code. What code is it actually generating? > Building a C compiler which can correctly compile sqlite and pass the test suite", "context": "", "use_case": "", "switched_from": "", "story": "Claude's C Compiler vs. GCC"}, {"id": 751075088, "item_id": 46942193, "url": "https://news.ycombinator.com/item?id=46942193", "by": "DSMan195276", "date": "2026-02-08", "version": null, "stance": "warn", "quote": "clearly that's not true unless they did some serious hand-waving with kernel config options", "excerpt": "Something that bothers me here is that Anthropic claimed in their blog post that the Linux kernel could boot on x86 - is this not actually true then? They just made that part up? It seemed pretty unambiguous to me from the blog post that they were saying the kernel could boot on all three arch's, but clearly that's not true unless they did some serious hand-waving with kernel config options. Looking closer in the rep", "context": "", "use_case": "compiling Linux kernel", "switched_from": "", "story": "Claude's C Compiler vs. GCC"}, {"id": 750737968, "item_id": 46921123, "url": "https://news.ycombinator.com/item?id=46921123", "by": "nextaccountic", "date": "2026-02-06", "version": null, "stance": "neutral", "quote": "the compiler itself is working, it's just that the path to the stdlib isn't being passed properly", "excerpt": "This is hilarious. But the compiler itself is working, it's just that the path to the stdlib isn't being passed properly https://github.com/anthropics/claudes-c-compiler/issues/1#issuecomment-3856377542", "context": "", "use_case": "", "switched_from": "", "story": "Hello world does not compile"}, {"id": 750679312, "item_id": 46917457, "url": "https://news.ycombinator.com/item?id=46917457", "by": "_lunix", "date": "2026-02-06", "version": null, "stance": "warn", "quote": "this compiler is far too lenient on what it accepts to the point where I'd hesitate to call it", "excerpt": "The comments at [1] are a bit _too_ trollish for me, but they _do_ showcase that this compiler is far too lenient on what it accepts to the point where I'd hesitate to call it ... a C compiler (This [2] comment in particular is pretty damning). Still, an impressive achievement nonetheless, but there's a lot of nuance under the surface. [1] https://github.com/anthropics/claudes-c-compiler/issues/1 [2] https://github.c", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 750575872, "item_id": 46910992, "url": "https://news.ycombinator.com/item?id=46910992", "by": "astrange", "date": "2026-02-06", "version": null, "stance": "compare", "quote": "I'm somewhat familiar with gcc and clang's source and it doesn't really particularly look like it to me.", "excerpt": "> 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/src/passes/iv_strength_reduce.rs https://llvm.org/doxygen/LoopStrengthReduce_8cpp_source.html https://github.com/gcc-mirror/gcc/blob/master/g", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 750555088, "item_id": 46909693, "url": "https://news.ycombinator.com/item?id=46909693", "by": "lambda-lollipop", "date": "2026-02-05", "version": null, "stance": "warn", "quote": "", "excerpt": "apparently [hello world does not compile...](https://github.com/anthropics/claudes-c-compiler/issues/1)", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 750521088, "item_id": 46907568, "url": "https://news.ycombinator.com/item?id=46907568", "by": "dzaima", "date": "2026-02-05", "version": null, "stance": "warn", "quote": "which is a fast path incompatible with the _mm_free implementation", "excerpt": "Clicked on the first thing I happen to be interested in - SIMD stuff - and ended up at https://github.com/anthropics/claudes-c-compiler/blob/6f1b99acb2f4ec2414592136c2009fe7713deec3/include/xmmintrin.h#L575, which is a fast path incompatible with the _mm_free implementation; pretty trivial bug, not even actually SIMD or anything specialized at all. (obviously) a whole lot of UB in the actual SIMD impls, but that can ", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 750465696, "item_id": 46904106, "url": "https://news.ycombinator.com/item?id=46904106", "by": "flakiness", "date": "2026-02-05", "version": null, "stance": "neutral", "quote": "claims to have the first line of dmesg", "excerpt": "https://github.com/anthropics/claudes-c-compiler/blob/main/BUILDING_LINUX.txt claims to have the first line of dmesg (which is shown using dmesg obviously.)", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}, {"id": 750461329, "item_id": 46903833, "url": "https://news.ycombinator.com/item?id=46903833", "by": "dmitrygr", "date": "2026-02-05", "version": null, "stance": "warn", "quote": "such arbitrary and shitty code as this", "excerpt": "> The generated code is not very efficient. Even with all optimizations enabled, it outputs less efficient code than GCC with all optimizations disabled. Worse than \"-O0\" takes skill... So then, it produced something much worse than tcc (which is better than gcc -O0), an equivalent of which one man can produce in under two weeks. So even all those tokens and dollars did not equal one man's week of work. Except the on", "context": "", "use_case": "", "switched_from": "", "story": "We tasked Opus 4.6 using agent teams to build a C Compiler"}]}