I think it is the novelty of the idea of what an LLM can do that is important. I suppose accuracy can be improved over time. Compared to using gmaps to search places, it seems to be a bit better.

Oh yeah I expect LLMs to revolutionize search/UIs but a broken demo is a broken demo.

I guess in this case it might be a flaw of the underlying data input though. If the locations aren't tagged then it's not going to pick them up.

So it's probably similar to google maps but the search is just more configurable.

Sounds like the current zeitgeist.

Seems like it should be useful beyond demos but we aren't sure what those use cases would be. Just need to wait for AGI and then..

I have actually spent about 20 minutes now and I can't think anything worth asking the model in this context.

I think with LLMs the tighter the constraints you give it and the bumpers the better it is. Something you could do with it is like a JackBox game that generates the content. However I think it is very dangerous to rely too heavily on it without writing something to kind of gate or filter the inputs.

Almost as if it needs data sanitization.