thisContext

This is devastating. :( Vanessa remains a profoundly strong and joyous presence in my life.

Through conversation, we can add skills to a model as new MCP tools.

Through simulation, we can specify the behavior of the virtual machine exactly.

AI can help us find the “desire paths” in stack instructions.

The core of the mechanism is working.

Server-side Caffeine can display in your web browser.

These robots know the value of keeping your hands on your instrument!

There’s a lot of Smalltalk knowledge in the pre-training data of most LLMs.

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 WebAssembly (WASM).

creating WASM from JS is a bit like creating DNA from proteins 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 automa…

Catalyst uses a synchronized linear representation of object memory to coordinate JavaScript and WebAssembly It’s straightforward to apply WebAssembly (WASM) to isolated JavaScript hotspots, where there are no side-effects.