Updates on 2022/4/28

It's very satisfying and remarkable that Monocle has almost completely eliminated the "I saw this somewhere, but I can't remember where, and Google can't find it" problem from my life. Almost completely. Online eidetic memory for the web.

I've been working on a conversational bot that I can brainstorm with and ask for advice. I've been tinkering with it for a few days, but today, I finally had a conversation that I thought was helpful enough for me to feel that it was adding value to my working process. Here's a raw (except for fixing some of my typos) transcript of the conversation (minus the prompt). The conversation is generated using GPT-J-6B running under my Calamity deployment.

Here's an excerpt:

Me: What if we present browser history as a map to explore instead? how do we lay out a map?

AI: One option would be to put the first node of the map near the top of the map, and have a node for each event. And then the second map layer might be a map to explore the details for a particular event in the first map. And so on.

Me: How do you think this compares to a geographic map? Can we draw some analogies to this "online history map"?

AI: There's a good analogy here that is actually very similar to what a geographic map is. A geographic map is basically a map that is made by plotting points of latitude and longitude on a flat plane, so they have a two dimensional layout. You can then put different data on top of that map, like cities, roads, rivers, mountains, etc.

Me: How does that analogy extend to showing more abstract browsing histories on a map?

AI: I think you'd have to start with the idea of mapping history to points of latitude and longitude. Then the second layer of information could be a set of different things that go along with that point. You could map history to a collection of objects, such as locations, objects, and/or actions.

Me: I like that. It's like there's a pre-existing "map of the internet" with different topics in different neighborhoods, and browsing the web is like taking a stroll through those neighborhoods. Your paths then show up on the map as paths you took.

AI: That's a good analogy.

It's still... not perfect (I ask it how to be productive, and it tells me I can sit on the bed and watch TV). But baby steps!