News for hackers. Stuff that matters.
Re:Schema on write is better to live by by pjdkoch on Saturday August 21, 2021 @08:06PM (#28261744)
I think the schema is already there. You can read and understand it, right? So its has more structure for you than just entropy.

How to capitalize this is indeed a harder question. My mind gravitates more towards something like GPT3. If you fed it all your memories (expensive, I know) and gave it a prompt of "I was thinking about a funny gif with a dog and a mug in a room on fire", it'd for sure get you the this_is_fine.jpg. But the answer is not quite what I typically see myself wanting. Instead, I want to navigate this graph (the understanding necessary to make the connection from the prompt to the jpg in the first place) myself, and see what's interesting and non-obvious there. That's what I interpret as "being able to talk with your zettelkasten".

Re:Schema on write is better to live by by hrishi on Sunday August 22, 2021 @03:05AM (#28263512)
Some thoughts: the schema is only partially there, at least for me. I can read and understand the content, but if I'm removed enough from when I first read or stored it, I've lost the context in which I was seeing it and the relationships within.

Having something that models the mind is the absolute goal - that would be amazing. It's definitely possible, and a lot of this labour might equate to needing to have a good sense of direction and map-reading skills before we had GPS.