|
|
|
|
|
|
by tavavex
900 days ago
|
|
|
I'm curious - why would an earbud-activated LLM be preferable to just the normal interface with typing in the request? And why GPT specifically? I can see the point with technologies that integrate directly into the surrounding environment, like using Google Lens to look up information about a real object, or translate printed text, and so on. But the LLM will still be a text generator either way - is it just about being able to dictate a request out loud and have the reply be read back? |
|
|
As for the type of interface, having a screen requires eyeball attention that I rather have on the task at hand. This would remove the "device in hand" that a commpad/smartphone/tablet requires.
Me @ Kitchen: tap earbud & speak "read my favorite apple pie recipe list of ingredients" as I inventory the pantry.