Intelligent generation of content possible?

After a while, our vaults will be filled with tens of thousands of notes, and there are more to come each day. These huge number of notes are impossible to process.

Suggested features include elementary one and advanced ones.
Elementary ones: auto attaching referenced sources(pdf, pics, graphs), adding tags, auto including relevant information, etc.

advanced ones: Auto-generating new information/content/ideas/connections based on current notes in the vault. This can be implemented by deploying machine learning methods, which was trained by existing books/courses/internet content.

4 Likes

This is dream :smiley: Google GPT-3… maybe later it will be possible.

2 Likes

I’ve been checking out some open source ai’s and I have a feeling that one of these may have the potentials you’re looking for.

1 Like

Please let me know if any of those work out for you! :slight_smile:

This one looks promising for your specific needs.

Anyone out there is experimenting with these sorts of systems?

There are a lot of challenges about to scale a vault to thousands of notes.

Perhaps we can develop some sort of ‘lab’?

I have early access to this site, but I still to figure it out

Edit: I wasn’t active there and I lost access :frowning:

1 Like

Super interesting topic! I learned about Flowrite (Disclaimer: Referral link to get earlier access) | Flowrite yesterday that seems promising.

Also a fun discussion on HN about how AI like this is now ADDING fluff instead of reducing noise (and why that may be good, too).

3 Likes

From the same people: How we got access to GPT-3 in 5 days :crazy_face:

1 Like

Guys, Thanks for all the suggestions. There are a lot to be done in this direction. But we can start with easy one, like some context-dependent automation and an elementary intelligent suggestion algorithms that can detect what you are doing and suggest some relevant things to you real time. This suggested sth may be sth new.

1 Like

I have access to GPT-3 and I’ve played around with it some. It would be interesting to see how it could fit into something like Obsidian.

2 Likes

I’m in! Building some ML stuff for my bookmarks right now and want to extend it to my notes at some point.

Anyone want to start simply and build a tag recommendation plugin (reads current note and connected notes and extracts import keywords)?

Hi @eagle what things you imagine ‘it’ suggesting?

I never had the opportunity to play with GPT-3, but I’m very curious how this could fit the Note-taking picture.

I’m pretty sure that many people would feel great when being helped to generate specific types of repetitive content, like some office work, forms, things with known structure.

Perhaps using it in a personal vault would generate lots of noise and ‘distant’ text. The note-taking activity is rather intimate, needs emotional involvement; here, more is not better (at least for me).

But it would be cool to give it a try and discover when one could use this.

I would like something that helps me diminish complexity, which proposes to delete some notes, merge two notes that are too similar, summarize, etc.

I’m curious with what are you doing with your bookmarks?

With obsidian notes I’m experimenting with showing text of other notes that is similar to my current text. Also doing page-rank to my notes. It’s really useful.

I’m building a recommendation engine for my bookmarks. Right now it’s based on TF-IDF. I tried fancier embeddings like bert and doc2vec, but I’ve had the best results with TF-IDF.

With this similarity metric, I’m trying things like building a graph based on the top 5 most similar and then running some type of clustering on top of it.

It’s actually working surprisingly well and was born out of me not wanting to carefully organize every blog post, article, and paper I find interesting. It’s gonna be the first filter I use to determine if I want to distill an information source into my obsidian knowledge base.

It’s cool to hear your also using ML to understand your notes I think there’s a huge opportunity for this!

like, existing notes that may relate to what u are currently editing