Comments URL: https://news.ycombinator.com/item?id=45079165

Points: 2

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=45071388

Points: 1

# Comments: 0

It’s less “chat with AI,” more structured exploration. Curious if this feels useful for your own deep dives.

Comments URL: https://news.ycombinator.com/item?id=45057902

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44885532

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44873154

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44804882

Points: 2

# Comments: 2

I go into several rabbit holes in LLM conversations, and while chat is great in the moment, I quickly lose track of the body of knowledge that I covered. Backtracking and multi session usage becomes annoying.

So I'm building out proread, where an AI agent maps out your conversation continuously, so you can easily backtrack/recall, and come back to the same space across conversation sessions. This is helpful for deeper understanding of any topic, and you can also upload/search for docs. Under the hood is an agent that does all the work for you.

I hope you try it and give me feedback!

Comments URL: https://news.ycombinator.com/item?id=44741421

Points: 3

# Comments: 0

I got sick of copy pasting everything I'm reading through deeply into ChatGPT and getting lost in walls of text.

I'm building a new map like interface to understand any topic deeply. As you chat, your map gets built out, kind of like a nice notebook. You can search the web and pull in/upload documents in any format (pdf/epub/html), create maps over those docs for deeper understanding. You can also listen in podcast mode to your map for complete control over what you're listening to. You can semantic search docs, but also the interface has chapter level awareness of each uploaded source.

Samples are also available at proread.ai/pgessays , proread.ai/books , proread.ai/llm-papers.

Here's a couple of recent spaces I was consuming lately 1. economics - https://www.proread.ai/share/3fd6fa9d-5aea-4dd1-a190-eb83a6a... 2. the dollar weakening - https://www.proread.ai/share/3ca2565f-96ed-4abf-a523-e32b591...

Comments URL: https://news.ycombinator.com/item?id=44718596

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=44610772

Points: 3

# Comments: 0

LLMs have made me feel like I can understand anything, but I’ve been frustrated trying to truly understand ML papers using just ChatGPT or static PDFs. Summaries can help, but then I have to go back to the paper and read it linearly to deeply understand it, and I have long chatgpt conversations which I just can't track. So I built an interface designed to support a non-linear, brain-like exploration of papers — paired with a tutor in a chat interface that guides your understanding.

Try it out at: proread.ai/llm-papers

Knowledge maps let you see how ideas within a paper relate to each other and how papers connect across a field. Start with my curated maps of foundational LLM papers or build your own for any paper/set of papers you’re reading. You can also listen to the map as a podcast.

You have a chat based tutor as with ChatGPT but your questions keep updating the knowledge map so you don't lose anything

The map itself is an editable notebook which allow you to take notes, mark concepts as completed, tag concepts, and construct your own mental model as you read. You can not only read summaries but can go down to actual source content in readers where you want to.

You can make your own space with your own papers or other docs (PDF/txt/html/URLs) and create interactive maps personalized to your research or study needs.

The goal is to move beyond linear reading or static summarization: to create a space where understanding evolves dynamically, like how you actually think, with a tutor helping you make sense of it all.

Please try it out at: proread.ai/llm-papers

I’m looking for feedback from other researchers or paper readers — would this kind of non-linear, guided exploration help you understand tough topics/papers better than traditional PDFs or chat tools? What’s missing or confusing?

Thanks!

Comments URL: https://news.ycombinator.com/item?id=44468963

Points: 3

# Comments: 0

I've always found PG's essays incredibly valuable, but there's a problem: they're scattered across 20+ years and 200+ pieces. You read "How to Get Startup Ideas" and it's brilliant. Six months later you read "Organic Startup Ideas" and realize they're deeply connected, but you've lost track of the specifics; the connections get lost.

So I organized his essential insights into 6 focused knowledge maps covering startup ideas, wealth creation, great work, programming, design, and writing. Each map shows you the big picture first, then lets you drill down to specific concepts and source material.

Key features: - Interactive hierarchical maps that show how concepts connect - AI Q&A to explore ideas and get insights from the source material - Clone any collection to edit, annotate, and build upon with your own research, and share with friends - Create your own knowledge maps using PDFs, URLs, or web search

The goal isn't to replace reading the original essays, but to give you a scaffold for understanding how his ideas fit together. Once you see the landscape, you can dive deeper into whatever interests you most.

Looking for feedback if you try it!

Comments URL: https://news.ycombinator.com/item?id=44428555

Points: 1

# Comments: 0

What it does: - Upload research papers (PDFs) and web sources (HTML) - AI generates interactive knowledge maps from your sources - Skim read at a high level or read per-source/section summaries - Expand/build further specific sections of the map that interest you - Read original sources in context - Ask questions about the research and get contextual answers

I have curated some reviews on LLMs, Diffusion Models, Vision Language Models, AI Agents, Robotics, and Text-to-Speech.

Why I built this: I was constructing lit reviews with ChatGPT and getting lost in the walls of chat; I wanted to make a better experience for myself.

Please give me feedback on the UX/anything else!

Comments URL: https://news.ycombinator.com/item?id=44311972

Points: 5

# Comments: 1

Would love your thoughts on the interface, and whether this would be useful in your own work or otherwise.

Comments URL: https://news.ycombinator.com/item?id=44273539

Points: 8

# Comments: 1