alt Hacker NewsCame here to say this, too - creepy. Especially when there is no person in the loop, just an LLM agent responding on someone's behalf in their voice.
Came here to say this, too - creepy. Especially when there is no person in the loop, just an LLM agent responding on someone's behalf in their voice.
Isn't the point that it prepares the response, shows it to you along with some context to you. Like a sidebar showing who the other person is with a short summary of your last comms and your calendar. It should let you move the "proposed appointment" in that sidebar calendar and it should update the response to match your choice. If it clashes and you have no time it should show you what those other things are (maybe propose what you could shift) and so on.
This is how I imagine proper AI integration.
What I also want is not sending all my data to the provider. With the model sizes we use these days it's pretty much impossible to run them locally if you want the best, so imo the company that will come up with the best way to secure customer data will win.