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 experienc...
Stories by kanodiaayush
I'm building out Kerns, as an AI environment for research. You can seed a space with a topic and multiple source documents, and complete your research completely in one space. There's interactive mindmaps for exploration, podcast mode, powerful source readers with original plus chapter lev...
Most research tools help you collect links. Kerns is built for ongoing research.<p>You define topics and sources once. Kerns continuously tracks them over time, surfaces what changes, and structures the material so understanding compounds instead of resetting each session.<p>The key difference is th...
I feel like LLMs can help me understand anything. However, jumping between ChatGPT, tabs, and docs gets in the way of building real understanding beyond isolated summaries and questions. This is my attempt at fixing that — for lifelong learners, researchers, professionals and students.<p>Would love ...
When I do real research — reading papers, books, or trying to understand a complex topic — it never happens in one sitting.<p>I explore a bit, get interrupted, come back days later, ask new questions, find new sources, and gradually build understanding.<p>Existing AI tools are great at answering que...
Deep research rarely happens in a single pass. For high-stakes work, or to deeply understand something, you run many deep researches in parallel, revisit them over time, and synthesize understanding gradually. We combine deep research with other docs.<p>Kerns is built for this mode of research.<p>It...
Since LLMs came out, I’ve been amazed at how much faster I can learn. But I wanted one place to truly understand a topic across multiple sources (docs, books, web).<p>I’m building Kerns to solve this. Spaces are interactive collections that let you:<p>1. Explore a map from summary to high-detail<p>2...
LLMs are a great way to understand things with. Current methods are however engineered only for brief chat like interactions, whereas deep understanding requires continuous research, exploration and deep reading too.<p>Kerns is an AI interface designed to help with all of this - there's a power...
LLMs make us feel like we can learn anything, but chat is just one primitive. I'm trying to build interfaces which let us cover a topic our sources at length with AI.
These interfaces let us consolidate our understanding at glance so we don't get lost in long chat message histories, zoom i...
I'm building out Kerns, an AI environment for research. You can seed a space with a topic and multiple source documents, and complete your research completely in one space. There's a powerful chat agent which can reason across tool calls, and give cited answers. These citations take to a r...
I'm trying to build a better artifact than text summaries to explore a body of knowledge. I'd like to be able to start high level, and go as deep as I want to, in a unified experience.<p>Please try it, looking for feedback!
I wanted to be able to read summaries for some chapters, while reading source for others. Further, when I find some part of summary interesting, I want to immediately 'zoom in' to source for that part of text. Kerns reader supports this first class - see examples at <a href="https:/&#...
Post ChatGPT, I found that I could turn passive chapters in books to summaries; but when I wanted to dive back in to them in parts where I found them interesting, I'd have to map from summary to source manually. Further, I couldn't switch to audio seamlessly.<p>This is an interface where y...
Hey HN — I made Kerns because long, static writeups felt awful for deep learning. On Kerns a “space” is a structured learning environment: a top-level map, concise summaries, linked sources, a search/chat agent, audio version, and a fork button so you can re-organize the material and experiment...