We need to address the surge in AI-generated #Resources topics

[renevanderark]

I see this devolved a little after all.. maybe we could go about this analytically and first try to define what we’re talking about.

Is this the kind of post you mean?

LLM Toolkit: local and cloud LLMs from GDScript, with JSON you can trust

My character generator has a language model write whole characters as JSON, and the hard part wasn’t the requests, it was trusting what came back. Local models wrap JSON in prose, drop commas, ignore enums and run out of tokens mid-object. So I built the layer that deals with that, and packaged it as an addon. One API for LM Studio, Ollama, llama.cpp, vLLM, OpenAI, Claude and any OpenAI-style server Streaming on HTTPClient, polled once per frame: no threads, no frozen frames, UTF-8 split acros…

Or is this high enough effort? Hard to tell for me because I’ve been all effort all the time all my life (and still not part of the billionaire club somehow)