[ryanklee]

> I can't for the life of me think of a reason I'd need an AI to do any of the stuff I use my desktop OS for.

If the key can flexibly consume whatever content is in the current context -- images, audio, text, selectable files -- and potentially have access to RAG, it seems to me that the number of potential use cases is very high.

Of course, everything hinges on "flexible" -- if it's mono-modal and doesn't access context in an intuitive way, it'll be tough for it to find a place in people's workflows.

[shdon]

My question wasn't about the key per se (which is just a trigger for Copilot, it seems), but about what Copilot itself brings. Can it do any of the stuff you describe?

[ryanklee]

I'm addressing your particular point about not seeing any use for this in the OS. I disagree. If there is a flexible layer that can consume and correlate context, there are tons of use cases

[shdon]

Then indeed there might be. I'm not saying AI is useless in general, even though it might be totally irrelevant to my personal workflow. But my question is still what Copilot brings. Does it do what you describe? If not, what does it do?

[ryanklee]

Yeah, I doubt it does anything close to what I'm talking about. If it did, it would be a massive leap forward in integration. More likely, the button opens up Copilot side-bar and only takes text input. But we shall see. Maybe some RAG going on, maybe a bit capable of multimodal, but I'd be a little surprised if there's more than the usual "prompt LLM here".