Re:Toit v2.0.0
by dofm on Tuesday November 03, 2026 @08:35AM
(#50351813)
Thank you for your reply — I think it sounds like you're in a good place here.
I still definitely wish this wasn't something we had to care about still, but for a while at least I suspect it is.
I am a small/open-weights LLM enthusiast so at some point I will test this a bit more, because I tend to use LLMs close to bare-metal where prompts and skills are concerned, due to limited context. (In general I think post-training of smaller coding-oriented models like Muse Glimmer and Qwen has made long system prompts and extensive skill files far less significantly important)
Muse Glimmer (the model that happens to be running right now on my desk!) seems to have some knowledge of Toit without searching the web.
e.g. I asked it: "Could you write an embedded webserver that blinks the LED the number of times specified in a GET query string parameter?"
And what it wrote without access to documentation appears to be plausible (from what its human overlord can see from the documentation at least).
I still definitely wish this wasn't something we had to care about still, but for a while at least I suspect it is.
I am a small/open-weights LLM enthusiast so at some point I will test this a bit more, because I tend to use LLMs close to bare-metal where prompts and skills are concerned, due to limited context. (In general I think post-training of smaller coding-oriented models like Muse Glimmer and Qwen has made long system prompts and extensive skill files far less significantly important)
Muse Glimmer (the model that happens to be running right now on my desk!) seems to have some knowledge of Toit without searching the web.
e.g. I asked it: "Could you write an embedded webserver that blinks the LED the number of times specified in a GET query string parameter?"
And what it wrote without access to documentation appears to be plausible (from what its human overlord can see from the documentation at least).