When you ask stuff in your car on android auto it uses 3.5 flash-lite. The response details would include it in the logs.

Flash lite is very noticeably more idiotic than 3.8 Flash. It's why the quick AI overview is often much worse than the AI mode one.

The model used is irrelevant when there's the critical issue where their "AI" assistant can't understand the word "nearest". Literally worse than a second-grade understanding of English.

I also have had shockingly bad results with gemini on android. Ended up giving up on it after a few months. Silly silly google with their trademark UX polish and attention to usability.

As an android user, this worked perfectly like 10 years ago.

Yes, there's been a huge degradation in the reliability and usefulness of Google's digital assistant following its incorporation of "AI".

It's really puzzling. I was really happy with the original assistant, now it feels slower at literally everything.

Nothing too puzzling really. It was a good assistant specialized for a relatively narrow set of tasks and tooling on a much more modest chatbot architecture. Now it has a wider set of tools it can use, but is also computationally more expensive, so it runs slower. Makes it better if you want to do any task, but if you want to do a task like set the timer, the old model is obviously faster

The bigger issue is that it doesn't "know" what its capabilities are, and if you ask it to do something it can't do, it's likely to LARP doing them instead of telling you it can't.

The puzzling part is that it can't fall back to a dumb assistant for stuff it could always do. The slow part has not just been interpretation of the task, Gemini is actually slower at doing the task.