With vision models (SOTA models like Gemini and ChatGPT can do this), you can take a picture/screenshot of the button layout, upload it, and have it work from that. Feeding it current documentation (eg a pdf of a user manual) helps too.
Referencing outdated documentation or straight up hallucinating answers is still an issue. It is getting better with each model release though
I am switching next week when my new phone gets in. Between Siri, vanilla bugs, ios 26, and questionable design decisions, I'm going to try Android. I will say my 13 Pro is a beautiful piece of hardware but the software shortcomings are beginning to pile.
Other than blue bubbles, you aren't leaving behind much nowadays. Apple is now lagging in general usability vs competitors, Siri as one glaring example.
I ended up trying them around 2 decades ago (I do not recommend lol) and learned so much from that site. The information about the long time for it to take effect (1.5 hours AFAIK), warnings to take the right dose and no more, and the vision side effects the next day, along with horror stories of what could go wrong, Erowid probably saved us a trip to the ER or even worse.
Eg: A chatbot assistant is much more tangible to the regular joe than blockchain technology