“The mark of a good knowledge management system is it’s able to surprise you and it’s able to be a good conversational partner…it’s reminding you things you thought before” – Conor White-Sullivan
When people engage with LLMs, they ask for suggestions, refer to shared history and context, and build on previous responses. Their top expressed need is for systems to have a back-and-forth with them, to help them learn, to help them narrow things down, and to let them know what the system needs to provide better responses.
Because if you strip LLMs to their essence, they are just a much better way of using statistics to aggregate human intelligence and connect everything we’ve all done together to get more use out of it.