Make Science
Intuitive

Co-author intuitive explanations of scientific papers with your AI agent.

your tools/your agent/your credit

Explain a paper through video or an interactive example.

works withClaude Code·Codex·Cursor·Gemini CLI·any MCP-compatible agent
InteractiveWhy “it” means the animalExample
self-attention · illustrated
it → animal0.62
Trace “it” to

“Animal” is the strongest connection in this illustrative pattern.

How it works
01 · Open
Open a paper in your browser
Find a paper you want to understand. Bring its link to Open Intuition to get started.
02 · Author
Co-author with your agent
Copy the paper’s prompt into Claude Code or Codex. Work with your agent to make the idea click.
03 · Publish
Publish when you’re happy
Review the result and refine it together. When it feels right, publish it for the next reader.
↷ every explanation points back to the paper — and pulls the next reader in

Recent explanations

Browse all →

Why you can't predict spending: Hall's random-walk consumption (2026 Nobel)

Robert Hall's 1978 paper turned consumption research upside down: if households are forward-looking, today's spending already contains everything they know, so changes in spending should be unpredictable. The video builds that intuition, shows how Hall tested it on US quarterly data from 1948 to 1977, and explains why it became a foundation of the New Keynesian models cited in the 2026 Prize in Economic Sciences.

How do you count AIs? One Wi-Fi crime, one A-corp

A short explainer that follows the paper's own Wi-Fi crime hypothetical. It shows why the law has to count AI agents by their goals, and how the proposed "A-corp" (an AI-run company with a known human owner, cryptographic keys and scoped tokens) traces actions to a human (thin identity) and pushes AIs to organize into coherent, sanctionable units through incentives and selection (thick identity).

POET: grow the challenges, share the solutions

A short narrated explanation of POET's paired environments and learners, environment mutation, and performance-tested transfers. Original schematic animation; based on Wang, Lehman, Clune and Stanley, arXiv:1901.01753v3. The experiments are bounded 2-D walking studies, not proof of unlimited progress.

The Catalyst That Keeps Time

Why a catalyst that holds still must compromise, and how a ruthenium crystal stretched and squeezed in rhythm, in the authors' simulations, makes ammonia ten times faster than unstrained ruthenium and pushes the reaction past the balance point a still catalyst is stuck at. A 6-minute explainer for computer-science readers, with physically lit 3D, redrawn figures and the paper's drive heard at its real rate. One disclosure: the paper's Fig 6B and Discussion show 350 switches per second settling below balance at 50 atm, while one sentence of its Results lists 350 Hz among the frequencies that raise conversion; the video follows the plotted curve (details in the README).

Create your own

Connect once. Then just
talk to your agent.

No rigid commands. Describe the paper and the intuition you want to land — in your own words — and your agent builds it with you.

works with
Claude Code — running on your machine
Setup · once (shell)
$ claude mcp add --transport http open-intuition https://www.openintuition.org/api/mcp
then run /mcp in Claude Code to sign in
After sign-in, open-intuition tools become available to your agent
THEN JUST CHAT WITH IT — IN PLAIN ENGLISH
you
I keep losing the thread on self-attention in 1706.03762. Build me an interactive where I hover a word and watch what it attends to — start with why “it” points at “animal.”
Read arXiv:1706.03762 §3.2. I’ll wire hover → attention weights and highlight the strongest edge. Building a draft on your machine…
you
perfect — make the winning edge terracotta, then open the draft