Just my two cents: If you're saving enough documents to where you need something like this, you're spending too much time bookmarking and not enough time actually making use of the knowledge contained in there. I'm sure it's an improvement for those people though.

Would be even better if AI systems were integrated with hypergraphs of the sort, which was an approach some AGI projects were taking 1-2 decades ago.

For me bookmarking does not mean that I want to read the article, it usually mean that I think it may be useful for certain task in the future want it to be in my search result some times. Since sometimes I want to read in depth about something that I read briefly long ago, it is really hard for me to find it back.

It's like a personal/curated library. I don't see what's wrong with that. Whenever I start thinking about some article or other I vaguely remember and want to re-read it, but can't find it again without substantial effort, I wish I'd been more fastidious about saving and archiving that article.

You see it best in how Luhmann used the Zettelkasten system, where ideas and resources are linked to topics that he wanted to think and write about.

I've found web bookmarks don't even need to be sorted into folders. You can always search the bookmarks if you remember a fragment of the title, else just scroll back through them manually until you find it.

Knowledge Management sometimes is just elaborated procrastinating

Perhaps all of life is just elaborated procrastination. We stumble onto the stage, busy ourselves with something and then we’re gone for eternity.

But building something and sharing it with others: if it is procrastination it’s quite productive procrastination.

I still recall when a young dude thought the knowledge management at CERN could do with a bit of elaborated procrastinating… and we got a WWW out of it.

Hey, I resemble that remark…

I did develop this when I was PhD student in NLP. I think it's fine to learn to develop a personal search system if you want to learn.

> you're spending too much time bookmarking and not enough time actually making use of the knowledge

Exactly!

Just like if you are always writing in a journal like DaVinci, Curie, Darwin, or Edison, you're spending too much time reliving the past instead of inventing the future.

> Just my two cents: If you're saving enough documents to where you need something like this, you're spending too much time bookmarking and not enough time actually making use of the knowledge contained in there.

I completely disagree, I keep running into the opposite problem: Having to retread ground on old projects because I didn't document what I did and forgot over time.

I even notice other people have this issue. I recently took over a project from a friend, but because he didn't document anything, I'm essentially starting from scratch.

I have never once regretted writing something down, but I constantly regret not writing something down.

Author here, I like the idea to have a public and personal search-engine. I'd love to deep dive in some people bookmarks such as expert in NLP field in order to get clue / a point of view on problem I want to solve but those informations are not available most of the time

You might get lucky and find a NLP expert's bookmarks on https://pinboard.in.

Not sure if it’s just on mobile but the demo completely destroys the back button.

Kudos to the developer for sharing this impressive personal knowledge base project! I love seeing the passion and technical creativity of this community. Experimenting with tools for surfacing serendipitous insights and connecting ideas is what moves us forward. Keep up the great work - I look forward to seeing how you evolve and refine this system further!

Loved it. Great job. Looking forward to new updates.

This looks similar https://github.com/KnowledgeCanvas/knowledge

Thank you for this ! Knowledge is primarly inspired by http://www.semanlink.net/sl/home

How do you make it useful though?

It upload content some of my friends like (github stars) and they have very good taste, so when I'm looking for a document / information on a new topic in machine learning or databases I like to give it a chance

Ridiculous how easy Asturiano makes it to say "3d? Ah go on then, why not."

Amazed by 3d-force-graph js library

Looks great! I wonder is it API based or utilising a local LLM?

The ask button is provided by chatgpt api here

Very cool!