As of 2022, https://get.mem.ai/mem-x has one of the best AI for Notes integrations. I'm sure 2023 will be fruitful. I'm already seeing some Obsidian/Local experiments.

> making connections between notes > related notes in it's context.

Mem -> similar mems

Obsidian -> https://github.com/brianpetro/obsidian-smart-connections | https://github.com/deepfates/silicon

> asking questions/searching

Mem -> search is NLP/AI by default

Markdown -> https://github.com/debanjum/khoj

Obsidian -> https://twitter.com/Sarah_A_Bentley/status/16110695760993362...

> new (summary) notes based on (many) old notes

There are a lot of summarizers on the web. They work great on whole articles. The problem is, how do you summarize hundreds (and more) of independent/related smaller notes ?

Mem is kinda nice but it’s pretty lame that even after those millions in vc money they still don’t support math notation.

I do need something like that. I think "location based reminders" in ios/android come close, but wouldn't this be cool...

Type out a list of things you need to do in code:

  1. We need to accept batch applications not just one
    1. To accommodate this, we need a new parameter in the Gizmo accepting function
    2. The REST API needs an optional new parameter to accept an array of applications. The code in this function also needs a new error if the array is populated as well as the old parameter for the single application.

Then say in VS-Code a special thing would go in and find all locations in the code that match this and show files that need adjustment. The files would be clickable and when you scroll down see visual annotations of the areas that need change.

I have a husky and so I often have to go for multi mile hour long walks frequently throughout the day. During that time I use voice dictation to text to work on new projects, articles, etc. by virtue of the fact that I am dictating them in an ad hoc manner they're frequently haphazardly written, disorganized and rife with grammar and spelling issues.

With the zero shot learning of chat GPT, when I get home I'm able to drop them in and it'll spit out a polished version of them. It has been saving me hours of time.

What do you tell chatgpt exactly to get them into polished shape?

Reflect: https://reflect.app/home

Just released an integration with OpenAI's GPT3.5 (not to be confused with the ChatGPT product) which allows you to do all sorts of really cool things with your notes like summarize, argue against an idea, or for it, etc. Basically anything you can do with GPT is accessible directly in your notes.

Also it's E2E encrypted so your notes aren't the product, which I really like.

I am experimenting with an AI based classification system.

Right now I am using it as a smart news reader with a single class "do i want to see more articles about this?" It works, but I don't think this kind of content-based filtering is going to be competitive with collaborative filtering for most people and why this is not a product on the market despite having been technically possible since the early 00's.

I am thinking about extending it to take an ontology and learns models to automatically put tags on documents, images, things like that and more generally set up some workflow where it learns how to perform certain steps on its own.

Logseq has a GPT3 plugin: https://github.com/briansunter/logseq-plugin-gpt3-openai

A related thing that would be very useful is an LLM-powered tool that extracts info from all your documents and bookmarks and answers queries.

Readwise's Reader has an AI assistant for summarizing snippets and helping you build better annotations.

I love notion, it just rolled out something like that: https://www.notion.so/product/ai