Comment by Syzygies
3 hours ago
As a mathematician, this reads to me as the most informed comment.
Various priors inoculate me from feeling some of the rejection expressed in other comments. I knew Sammy Eilenberg, perhaps the most famous mathematician to work at Columbia University. He hired me. With friends, I ran into him one night out in NYC, and in his 70's we all stayed out past dawn. His late career focused on topos theory, and everyone in the building politely rolled their eyes. Those are working mathematicians having an understandable reaction; most reactions to topos theory here are simply uninformed. The evolution of programming languages has lead from the lambda calculus to many forms of category theory. Topos theory would not be a surprise.
The Leech lattice? Could be a brilliant idea. Compare Lenstra's elliptic curve factorization algorithm. Sometimes famous landmarks in mathematics have remarkable properties; mining them for algorithmic advantage is no different than mining asteroids for rare metals.
The involvement of AI is most problematic. Mathematics fears being swamped by mediocre AI-authored papers, but the truth is "publish or perish" has long lead to mathematics being swamped by mediocre papers. Bad artists are losing jobs, but good artists are working faster.
I welcome a new era of programming language design, where AI makes rapid prototyping a reality. We just have to take sharing this work with a grain of salt. Stop reading when you lose interest, but welcome the churn!
Rapid prototyping was always possible in PL design. It was very possible to go from idea to a working proof of concept language with a couple weeks' work. There are thousands of POC projects like this that popped up before LLMs existed.
What LLMs are doing now is allowing people to take prototypes and to publish them with an entire 200 page book no one (not even the author) has read, and a polished-looking website filled with marketing verbiage and a cute logo.
What would be interesting to me would be to see the process of rapidly refining the design, but I keep checking back on these "Here's my exciting new 400kLOC LLM language project I made in 3 weeks" and they all seem to die very shortly after the splashy announcements a few weeks later, as the author seemingly lost interest.
Which is not surprising because that's the way it always went with little languages -- writing a language has always been a marathon, not a sprint. It's just before, a 200 page book was an indicator of author dedication. Now, a 200 page book is just more bytes for digital kindling.
Yeah, early on in my evaluation of this thing was to check out the contributors and their work. Was expecting this to be the product of at least a small group. Imagine my surprise to see… one person…