Pseudo, a Common Lisp macro for pseudocode expressions
funcall.blogspot.comSimilar idea: https://www.youtube.com/watch?v=ueGC3xVcDlc William Bowman: First class Prompt Engineering with llm lang! (This is a bad idea.) (RacketCon)
I like it, and indeed neatly shows the power of Lisp. The JS variety (well the one that I could come up with) is far less elegant, but works [0] (well, mostly). It really shows how the different LLMs stack up; some really cannot get anything right, but something like openai/gpt-4o-mini seems to get it right mostly (8/10).
Passing the lexical information in and requiring s-expressions be returned is a good idea. Put a cache on it to remember what the llm came up with last time and you have a legitimate, if somewhat weird, language implementation.
Cache it and give the user a tool to see the code and regenerate it when not happy and this is really quite a bit of fun.
That's kind of neat. I had an idea for a macro that would search GitHub for functions with the desired name and use their implementation, but this is probably more predicatable.
I see a bunch of 18+ ads.
I see none, it's a regular blog post (no ads there, just some code) page with a few comments (no ads there either). I am using an adblocker.
I get some ads (not using an ad blocker) but nothing NSFW.
This is Blogspot, unless something real weird is going on you’re just seeing normal Google ads. I have found, in my travels, that Google (Meta too) doesn’t moderate its ads as well as you’d expect once you leave the US.
I only see starlink ads.
After decades of research, we have finally come up with a way to make programs break in unpredictable ways on every compilation.
One could easily implement an Emacs (SLIME) plugin to "macroexpand" the (pseudo) expresion to real (concrete) Lisp code, and even to try again until the implementation satisfies you.
Then it becomes a concrete Lisp implementation and thus not unpredictable anymore.
Isn’t that just vibe coding with extra steps?
... and yet, the author will probably get an email soon with $500m VC offer for a revolutionary way of coding.
Can't commit pseudo-code to prod like this :laugh: cause you might get different results once in a while!