Yo i've been playing around with various AI sandboxes for a while now. Nat.dev and the like.<p>They are cool and all, however they seem very simplistic. I've always been expecting someone to drop some terminal-based extremely powerful AI editor client, but I haven't been able to find anything.
sdk.vercel.ai is also a nice playground where multiple models can be used for interaction at the same time. Regarding this application scenario, is it used to compare the quality of model responses? Although there are many large model evaluation organizations now, for ordinary users, common standards often fail to guide the correct choice, after all, everyone's use case is different.
Obligatory Ollama link: <a href="https://ollama.com/">https://ollama.com/</a><p>May be of interest.<p>Check out Ollama's Modelfile, too: <a href="https://github.com/ollama/ollama/blob/main/docs/modelfile.md">https://github.com/ollama/ollama/blob/main/docs/modelfile.md</a>