Since January I've been working on a storytelling system that fuses what I think is the best of interactive fiction / MUDs with the strengths of LLMs. The world model is entirely deterministic, but the LLM interprets the player and narrates the game and NPCs.
Also hacking on something similar to YC's QM but designed for small non-profits to ease as much back office work as possible.
I have not run any evals against it to see how schlaflos's quant compares to antirez's of the original. There are also some other ds4-compatible GGUFs on HuggingFace now.
That's fair, each provider maintains their own cache. OpenRouter does make an effort to keep providers "sticky", but it may hop/stick to another if latency is too high.
If you don't care about latency, you can create a preset with a single provider, then use that as the model key (i.e. `@preset/deekseek-v4-excl`). The only real downside is OpenRouter's service fee. If you don't want the convenience of switching models, or their excellent dashboard, it's definitely better to pay the provider directly.
Thats what I meant. I even looked it up before posting. I suspect that definite article must have slipped in because I‘m used to the Icelandic translation which uses a definite article in the title.
reply