August | 2025 | thisContext
1 post published by Craig Latta during August 2025| thisContext
What if we could compose LLMs from reusable circuits? It’s always bugged me that we can’t explain how large language models do what they do. It makes the models difficult to trust, poss…| thisContext
There’s a long tradition of just-in-time compilation of code in livecoding systems, from McCarthy’s LISP systems in the 1960s, to the dynamic method translation of the Deutsch-Schiffman Smalltalk virtual machine, to the “hotspot” compilers of Self, Strongtalk and Java, to current implementations for JavaScript and WebAssembly in Chrome’s V8 and Firefox’s SpiderMonkey. Rather than interpret […]| thisContext
I’m writing the Catalyst Smalltalk virtual machine in Smalltalk, and running it in WebAssembly (WASM, in particular WASM GC, which has a reference-types system supporting garbage collection),…| thisContext
The core of the mechanism is working. I’ve bootstrapped a Smalltalk virtual machine and object memory as a WebAssembly (WASM) module, using the type system that supports garbage collection th…| thisContext
Server-side Caffeine can display in your web browser. Tether is Caffeine’s remote messaging protocol. It enables messaging between multiple Caffeine systems running in web browsers, other Jav…| thisContext
These robots know the value of keeping your hands on your instrument! I’ve gotten up to speed on AI programming, and it didn’t hurt a bit. After learning the OpenAI chat and realtime AP…| thisContext
There’s a lot of Smalltalk knowledge in the pre-training data of most LLMs. I’ve been stumbling toward a “good enough” understanding of Smalltalk by an AI large language model, an…| thisContext
After creating a working proof-of-concept Squeak Smalltalk virtual machine with a combination of existing SqueakJS code and handwritten WASM (for the instruction functions), I set about automating the generation of WASM from JS for the rest of the functions. (A hybrid WASM/JS virtual machine has poor performance, because of the overhead of calling JS functions […]| thisContext
It’s straightforward to apply WebAssembly (WASM) to isolated JavaScript hotspots, where there are no side-effects. This enables us to speed up sections of the SqueakJS primitives, like BitBLT, which perform pure functions. The SqueakJS interpreter code, on the other hand, is rife with side-effects. The act of interpretation modifies the deep graph of connected structures […]| thisContext
continuing with the DNA theme… In Catalyst, a WebAssembly implementation of the OpenSmalltalk virtual machine, there are three linguistic levels in play: Smalltalk, JavaScript (JS), and WebAs…| thisContext
