I don’t know how tech savvy you are, but I’m assuming since your on lemmy it’s pretty good :)

The way we’ve solved this sort of problem in the office is by using the LLM’s JSON response, and a prompt that essentially keeps a set of JSON objects alongside the actual chat response.

In the DND example, this would be a set character sheets that get returned every response but only changed when the narrative changes them. More expensive, and needing a larger context window, but reasonably effective.

It’s got a nice component to go with it, so setting up is easier. I particularly use it for scheduling thermostats, and find it much more user friendly. Sure I could do it with automations, but I’d either have one, massively unwieldy one with lots of states and triggers, or lots of individual ones.

This custom component is what I use and love - https://github.com/nielsfaber/scheduler-component

I can’t decide if I want this to have been written by an AI or not.

Better than that, if you are after more than one (and with GU10s, who isn’t?)

https://www.ikea.com/gb/en/p/tradfri-remote-control-kit-smart-wireless-dimmable-white-spectrum-50517642/

This gives you 3 bulbs and a handy remote that also works with HA.

Thanks for the link. I knew nothing about him and that was cool.

Great answer, thank you!

Got any project details for that? A BOM, or even a link to an enclosure on things or printables?

Without going to whole hog and hosting my own infrastructure, what are some good alternatives?

I suspect this is a rendering/process thing rather than an accuracy thing. Have you tested if the logic of the first one isn’t listening to the other fields?

Thinking it through, in an ‘and’ test, you do only have to watch for the the state of the first clause, because so long as that is false, it doesn’t matter what the rest say. In the ‘or’ clause, you need to watch for the value of all of them.