I figured this was where Google Glass was eventually going, but with more emphasis on visual cues. Like, it'd use face recognition to show people's names above their heads, and could give you a history of when you last talked to them and about what, in a sidebar.
I even had the idea of keying off audio cues and doing google searches, to provide context. But, ChatGPT really changes the game, in conversations.
BTW, it's illegal to make audio recordings of people without appropriate warning. You can film or photograph people in public places, but not secretly make audio recordings of them. Not retaining the audio could land this in a legal grey zone, but it's not one I'd want to test in court.