Show HN: A visual AI interface to understand papers/books/topics | Hacker News Reader

topics

kerns.ai

17 pointskanodiaayush14 comments

I feel like LLMs can help me understand anything. However, after I get a summary, I can't dive in to parts that I find interesting; can't refer to original source easily and can't control context with chatbots. This is an attempt to solve for a complete knowledge consumption experience with AI . Please give me feedback!

Open articleView on HN

Looks very cool! How does it compare to notebooklm?

One feature that may be useful for others that I've wanted is constraining the info the the LLM uses from a given document. I'm self-studying from a math text with pdf I have loaded. Scenario: I'm working on a problem and I want to know if there's any useful theorems or definitions related to the problem, but only from the text up to the problem. I don't want it to give me results from anything in the future of the text, since presumably the author intended the reader to solve the problem using material only up to that point.

You can generalize this, but probably out of scope. Sometimes it's instructive to try to solve a math or physics problem using a restricted set of theorems or ideas. So it would be really cool if you could ask the LLM what results you have at your disposal excepting theorems x,y,z and all results deriving from those.

NotebookLM is in my mind an introductory product for deep understanding which does RAG and long podcasts well. However, strong understanding requires much more. We are still building out a coherent experience, but key ingredients are a strong exploration artifact (our map aims to be that), rich source control, context engineering (of the nature you pick up on above), and switching between modalities. We also have a powerful reader which lets us switch to various levels of summaries/original source on a chapter level, and jump between these easily. There's also friction in Notebooklm like you have to find web sources manually; our agent aims to do that from a simple text request. Going forward, we aim to add the ability to have a strong note taking experience (you can take hierarchical notes, AI assisted), and the agent should nudge you to complete what you are trying to achieve in a space.

In the chat agent, there's an option to turn off AI knowledge; and we are adding chapter level context control. I think 'start until upto this point' (and 'from this point to end of text') are great additions. Will add.

Regarding the generalization, I think with strong context engineering and powerful reasoning, this is hopefully achievable. But making a bespoke feature for this feels hard.

Thanks for your feedback!

Cursor and the agenetic IDEs are great for this kind of context control. Although designed for code, I’ve started using them for regular language, by converting large docs to broken-up plain text files (which it can do for you). Then you can @ whatever chapter you like in your questions

I was doing this for epubs in cursor too, which is what led me to building this product! Cursor is just not engineered to support the above across native file formats (pdfs/epubs).

I really need to get my POC out of beta and out in the world. This UI is polished, but there's several issues with it in terms of usability and extensibility and following the source of knowledge when it gets a large amount of sources

I think you'll have a few more iterations until you figure out that going with this visual graph style isn't optimal.

We are iterating fast and solving issues, indeed, and are aware of some problems.

It would be helpful to understand what you mean more precisely with the last line, particularly if you've experimented with this graph style and found it seriously inhibiting. Our assumption in fact isn't that the visual graph style is optimal for a LOT of depth. It is useful for some 'unknown' period of exploration. We have alternatively a tree representation of the same information, which we find becomes quickly better to use, once you have a lay of the topic and are more familiar with top level ideas. Then for specifi

This looks fascinating, and really well done! but I’m not sure I want to store it on your server. I’d be willing to pay an annual license for it, to be able to host locally. Bookmarking this!

That is great to know; thank you! Would you be willing to pay a bit extra for higher security tiers/privacy?

I’m not sure what you mean. A local app that I run myself would be the right level of security/privacy for me. Otherwise I have to trust your ability to write secure software, which is hard to prove

Yes, that's true. I think it is analogous to paying higher to Cursor for their no data retention policy, so its definitely trusting the provider further. It is of course possible that's also not acceptable, which is what I was wondering if it is..

Love this idea of branching chat history and visualising it as a knowledge graph. Also, the site looks very nice and works well on mobile. Wishing you success

Thank you!

As an Obsidian user, I wish this was part of it! Awesome project.

Thank you!

I love Obsidian too! It is unclear to me if I want to manage this kind of service on my laptop, or want fundamental cross device functionality to consume on phone when we want to. For now, web is our platform of choice.

Reply on news.ycombinator.com