RQ3: Can the memory requirements of a "micro"-controller be met by Joy? In order to process 99% of tokens, keeping up with the GPUs (in and out), it'll require using all cores — so the memory overhead for the language needs to be minimal. Bonus would be mostly static memory
@alexjc
-
Core Combinators Required for Functional Programming Systems
By
–
RQ2: Which core set of 'combinators' is necessary to get anything done? This has been my focus today! The original Joy implementation has many built-in primitives within the core VM: from the obvious function calling, looping and stepping through lists, to linear recursion
-
Joy Token Micro-Controller: Elegant Implementation for Efficiency Security
By
–
RQ1: What's necessary for Joy to work as a token 'micro-controller'? Are you wondering why I've been focused on an elegant implementation? I believe this makes two things possible: (i) efficiency needed to generate tokens during training, and (ii) security [additionally]
-
Joyfl v0.1: Minimal Python Interpreter with 342 Lines
By
–
v0.1 : Minimum Viable Interpreter Most notable is that the source code is only ~342 lines — from parser to interpreter, including terminal interaction but excluding comments! ▶︎ You can launch the REPL just by running the `joyfl` script with Python 3.10+. All the samples
-
Joy Programming Language Implementation Updates and Design Elegance
By
–
I should clarify… I believe the *original* Joy design by Manfred von Thun (see link) is the most elegant ever, not this implementation — yet? I'll post implementation updates in the thread below over the next week or so… https://
hypercubed.github.io/joy/html/forth
-joy.html
… -
Microcontroller Language for LLM Token Processing and Training Data
By
–
R&D: While I love coding up new languages just for fun, this project has particular #ML / #LLM research questions in mind… What if there was a language for a 'micro-controller' able to process 99% of tokens? TRAINING: To produce training data, what's the middle ground
-
Joyfl: Minimal Elegant Joy Programming Language Dialect
By
–
NEW: I just released a tiny project called `joyfl` — a minimal but elegant dialect of Joy. #joyfl Joy is a so-called 'concatenative' and functional programming language, introduced 25 years ago. I now think of it as the most elegant language ever!
-
AI Progress and Limitations Beyond Demo Settings
By
–
I agree you can probably break it if you interact with it outside of "demo-worthy" settings, but there is undeniable progress too. https://t.co/dh8HDLUMmT
— Alex J. Champandard 🌱 (@alexjc) 5 août 2025I agree you can probably break it if you interact with it outside of "demo-worthy" settings, but there is undeniable progress too.
-
LLMs Hallucinate APIs Zero-Shot Distance Minimization
By
–
Have LLMs hallucinate an API to your library zero-shot and try to minimize the distance.
-
Democratization of Creativity: What Wasn’t Obvious Ten Years Ago
By
–
Prototypes and publications from 10 years ago may seem prophetic, but I'd say most of it was obvious to many at the time.
— Alex J. Champandard 🌱 (@alexjc) 31 juillet 2025
The fun question is, what part of the "democratization" of "creativity" (good or bad) was not obvious 10 years ago? https://t.co/EyxpSeQ4IQPrototypes and publications from 10 years ago may seem prophetic, but I'd say most of it was obvious to many at the time. The fun question is, what part of the "democratization" of "creativity" (good or bad) was not obvious 10 years ago?