Tonk

A portable data substrate for humans and their tools to think together.

This network is a tree of beliefs about the future. Unlike a document I read, it's an object I use to think about the world. LLMs help me build it and keep it updated in a reasonable timeframe. I run calculations, toggle scenarios like "what if belief X resolves true" and watch probabilities cascade down the branches. Representing Thought in Carry Six months ago, I was attempting to build worlds using text documents. I wanted to model possible futures; more precisely, to simulate "what if" scenarios — for example, what if we live in a world with AGI? What if the world warms to 4 degrees? A rec

saved by

• Xi Da

related reading

• LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• LLM Daydreaming · Gwern.netgwern.net
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• Andrej Karpathy on X: "LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating" / Xx.com
• GenAI Handbookgenai-handbook.github.io
• Explore | alphaXivalphaxiv.org
• LLMs and World Models, Part 1 - by Melanie Mitchellaiguide.substack.com
• World Models: Computing the Uncomputablenotboring.co
• Building Effective AI Agents \ Anthropicanthropic.com
• 2025: The year in LLMssimonwillison.net
• As Rocks May Think | Eric Jangevjang.com