Interesting notes.

I'm disappointed even though it's entirely predictable that VisionOS is built on the iOS/iPadOS foundation rather than OSX. I guess we'll see how "walled in" it is but it's hard to see any reason Apple isn't going to be just as constraining and controlling about what happens on this OS as they are on iOS, if not more so. Which ultimately means I'll be very reluctant to ever adopt it in any meaningful way as my primary computing device.

Also it’s locked to Siri which is dogshit and falling further behind by the second. Apples speech to text is atrocious, the OpenAI tools blow it out of the water, as does Google’s.

No matter how fancy the visuals, it’s hard to have a pseudo-hands free voice interface that doesn’t uh, work?

if i understood the wwdc keynote correctly, they completely redid the text-to-speech, so this should actually be good now (maybe)

Yeah, but they’re so far behind even if they 10x Siri they’ve got nothing on OpenAI.

Then again.. Siri is all on device. I don’t want to send my voice anywhere

The current voice transcription engine at OpenAI is using Whisper-1[0] which is open source and runnable locally, if you wanted to keep it all on-device. I run it locally for various things and it works pretty damn well.

[0] https://github.com/openai/whisper