I Built a Scheme Compiler with AI in 4 Days
matthewphillips.info
I Built a Scheme Compiler with AI in 4 Days
1–10 of 34 posts
Re: I Built a Scheme Compiler with AI in 4 Days
#2What does "Write Yourself a Scheme in 48 Hours" produce? From OP I'm guessing it's something less than (73% of) R7RS.
https://en.wikibooks.org/wiki/Write_Yourself_a_Scheme_in_48_...
Re: I Built a Scheme Compiler with AI in 4 Days
#3detractors of AI claim this stuff is in its training data so it could be a copy which is valid. The crazy thing is the fact that it can definitely build something that does not exist.
Re: I Built a Scheme Compiler with AI in 4 Days
#4> I run into bugs all the time so it’s probably not ready for anyone other than me to use, but I’ve managed to go pretty deep (if not wide) in just a few days of work.
Having similar experience with my experimental code generator to Rust. Every time a yet another example does not work, Claude fixes it. However, I am curious whether it would converge to a bullet-proof solution, or I have to carefully read the code and come up with proper abstractions.
Re: I Built a Scheme Compiler with AI in 4 Days
#5Quickly building "near production level"? Are we talking about this Matthew Phillips?
https://docs.astro.build/en/guides/build-with-ai/
What a happy coincidence!
Re: I Built a Scheme Compiler with AI in 4 Days
#6What does "Write Yourself a Scheme in 48 Hours" produce? From OP I'm guessing it's something less than (73% of) R7RS. https://en.wikibooks.org/wiki/Write_Yourself_a_Scheme_in_48_...
The reason it's only 73% is because I prioritized fun stuff like self hosting and platform binaries. I think finishing off the standards would only take a few more hours (except eval which I don't plan to do).
Re: I Built a Scheme Compiler with AI in 4 Days
#7What does "Write Yourself a Scheme in 48 Hours" produce? From OP I'm guessing it's something less than (73% of) R7RS. https://en.wikibooks.org/wiki/Write_Yourself_a_Scheme_in_48_...
The reason it's only 73% is because I prioritized fun stuff like self hosting and platform binaries. I think finishing off the standards would only take a few more hours (except eval which I don't plan to do).
That wasn't a dig at you, I was just genuinely wondering what Write Yourself produces.
Re: I Built a Scheme Compiler with AI in 4 Days
#8Earlier quoted context omitted.
The reason it's only 73% is because I prioritized fun stuff like self hosting and platform binaries. I think finishing off the standards would only take a few more hours (except eval which I don't plan to do).
That wasn't a dig at you, I was just genuinely wondering what Write Yourself produces.
Yeah, I didn't take it that way, just thought it was worth clarifying that this isn't a case of AI hitting a wall or anything like that, I just went down other rabbit holes.
Re: I Built a Scheme Compiler with AI in 4 Days
#9Cool. I'm also working on a Scheme compiler for embedding. Bytecode VM as well as AOT compilation to Zig. 100% written by Claude Opus under my supervision and guidance. I've given it an extensive set of tests and benchmarks (r5rs and r7rs) which helps A LOT. I currently use it embedded in a modal prose editor, mostly running integration tests for now.
Re: I Built a Scheme Compiler with AI in 4 Days
#10> I run into bugs all the time so it’s probably not ready for anyone other than me to use, but I’ve managed to go pretty deep (if not wide) in just a few days of work. Having similar experience with my experimental code generator to Rust. Every time a yet another example does not work, Claude fixes it. However, I am curious whether it would converge to a bullet-proof solution, or I have to carefully read the code and…
if you're trying to write rust without thinking about the abstractions then yeah, its probably non-terminal. I would strongly suggest making the broad strokes yourself and letting it fill the details.