I don’t really want to prompt an AI system.
Instead I want it to passively watch what I do as I do things, talk to me to understand what I’m thinking as I do them, and progressively learn from me.
Over time, it should understands tacitly what it’s like to make certain decisions, and then do them.
Instead I want it to passively watch what I do as I do things, talk to me to understand what I’m thinking as I do them, and progressively learn from me.
Over time, it should understands tacitly what it’s like to make certain decisions, and then do them.
Comments
By that I mean either a rubber ducky or, to borrow from Llewellyn's strong-style pairing: talking in the highest level of abstraction the driver can understand.
A lot of what we do tacitly imply what we mean. If these tacit decisions and ideas aren’t made explicit, it’s impossible for an agent to really understand you well enough.
Just like training an apprentice, a true AI agent should amplify your abilities to the limits of how much compute you can buy, so that you can do a lot more with the same amount of time (which is true productivity).
An AI agent should instead do things exactly how I would do them.
Do as I do, not as I say.