Similar to your note on "Schedule-tuned", I could image models fine-tuned for use as the planning/reasoning engines for autonomous agents. This is a bit more general than taking a direct "command" as an input; the usual inputs would likely be "context about the state of the world", "goal", and "available tools".
Do you use Bard much? I use it fairly regularly, mainly for research. It seems to be kind of in between instruction-tuned and conversational. Do I have that right?
Similar to your note on "Schedule-tuned", I could image models fine-tuned for use as the planning/reasoning engines for autonomous agents. This is a bit more general than taking a direct "command" as an input; the usual inputs would likely be "context about the state of the world", "goal", and "available tools".
Do you use Bard much? I use it fairly regularly, mainly for research. It seems to be kind of in between instruction-tuned and conversational. Do I have that right?