What tech can do vs applying it requires it often to be configured and packaged to be usable in that way.

It also needs to work at least 99% of the time if not more. Not easy to do this with indeterministic models.

If my lights and heat were 99% reliable, I'd be getting new lights and heat.

I took 99% reliable as meaning not having to repeat the command, which given that Siri is something like 50% reliable by that metric, 99% sounds like heaven.

In those cases yeah, 99% isn't reliable enough. I'm not going to tolerate having power down for 3 days out of the year. But in fairness, home automation is less critical than that so 99% reliability is still acceptable to me. I don't think LLMs are anywhere near that, though, nor is there any sign of them getting there any time soon. So it does concern me to use an LLM as the backbone of home automation.

Depending on the use case, it is possible.

It is an adjustment coming from deterministic software and adding non-deterministic software to it, which can be improved by the quality of language and input into it.

Not easy, but doable, especially if it's a local model that is converting inputs into decisions and commands.

Cloud hosted models definitely can not always be consistent, but it's where I'm learning that prompt durability is a thing.