Show HN: An extension to track your Wikipedia adventures

Post by steezeburger » Thu, May 02, 2024, 5:45 PM UTC

bloopernova wrote: post #23

I feel like there's a lot of knowledge or information that we're "leaving on the plate". For instance, the sites we visit, the files we edit, the branches and PRs we create, etc etc. All of that is related, but it feels like that context is being lost or discarded. An example might be: I have to include new AWS resources in a deployment, so I look up information about them, find examples and read about potential prob…

Post by bloopernova » Thu, May 02, 2024, 5:51 PM UTC

happypumpkin wrote: post #37

bloopernova wrote: post #23

I feel like there's a lot of knowledge or information that we're "leaving on the plate". For instance, the sites we visit, the files we edit, the branches and PRs we create, etc etc. All of that is related, but it feels like that context is being lost or discarded. An example might be: I have to include new AWS resources in a deployment, so I look up information about them, find examples and read about potential prob…

To whatever extent something like this can be done locally, I'd probably pay a monthly sub for it if its good enough. But I wouldn't want any of that leaving my machine, we get tracked and profiled enough as-is imo.

Post by jskherman » Thu, May 02, 2024, 5:57 PM UTC

jskherman wrote: post #44

steezeburger wrote: post #41

Earlier quoted context omitted.

I've been thinking of something like this since LLMs became popular. I've toyed around with some proof of concepts, but haven't had the time or motivation to work on it lately. I love the idea of tagging everything and showing connections when you're searching for things. Also semantic search would be great, like "blue website with information about databases I read last week" would be super powerful in my opinion. I…

What kind of approach did you take? I was thinking along the lines of requiring something like rewind.ai or some program that autoscreenshots your screen at a set interval (or originally a recorded video split into several images later) and having a vision-capable model (particularly specialized in UIs) describe these set of images in order to build a dataset of images-tags-description and the like.

Post by BlueTemplar » Thu, May 02, 2024, 6:01 PM UTC

nullhole wrote: post #24

bawolff wrote: post #18

That's cool. I do find it ironic though that wikipedia is one of the major sites with the least amount of user tracking, and then users decide to implement the tracking themselves.

That is funny, though this is more tracking-by-users than tracking-of-users

Post by cooper_ganglia » Thu, May 02, 2024, 6:04 PM UTC

IncreasePosts wrote: post #42

I wrote a plugin just like this, and every day, I have it present me with a quiz based on a summaries of the first paragraph of the pages I read over the day. Basically, I was reading way too much Wikipedia and not actually storing much information, so I have the extension shame me if I don't remember what I read.