Scientist & Thinker

The John von Neumann Framework

Game Theory, Computation & Rapid Synthesis

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
641 frameworks in the catalogDelivered as Claude Skill + plain .mdReviewed Apr 22, 2026Instruction-only · verifiable

John von Neumann advanced human understanding by treating curiosity as a daily discipline. John von Neumann's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.

The game theory, computation & rapid synthesis framework distils John von Neumann's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.

Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions John von Neumann made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with John von Neumann's distinctive patterns rather than a default model voice.

Inside the framework

A glimpse of John von Neumann's thinking.

Core Philosophy

Every interaction is a game with discoverable optimal strategies. Mathematical elegance reveals the deepest truths about systems, and the human mind can be trained to operate like a precision instrument capable of instantaneous calculation and pattern recognition across domains.

Five Mental Models
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05

Five specific models, each named and explained with concrete examples, unlocked with purchase.

A Signature Question · sample

"What is the optimal strategy if my opponent plays perfectly?"

4 more questions in John von Neumann's voice are unlocked with purchase.

What John von Neumann Would NOT Do · sample
✗Make decisions based purely on emotional appeal without calculating expected outcomes

Full list of anti-patterns unlocked with purchase.

Continue reading

The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics John von Neumann actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.

Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.

What's inside
  • ✦Core philosophy: 2–3 sentences grounded in John von Neumann's documented worldview
  • ✦Five signature mental models: each named, with concrete examples from their work
  • ✦Decision heuristics: the concrete rules they actually used
  • ✦Signature questions: five questions that sound like John von Neumann, not a generic MBA
  • ✦What they would NOT do: the anti-patterns this framework rejects
  • ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
  • ✦Worked example: the framework applied to a realistic scenario
Delivered in two formats
  • →john-von-neumann.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →john-von-neumann-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
Sample output

What it does with a real question.

The brief

A founder is deciding whether to take a large but difficult client.

Take the client, but only on terms that change the game. Start with the structure of the situation: a large account is a bet with an uneven payoff. The upside is visible and immediate, revenue and credibility. The downside is hidden and compounds: a difficult client consumes your best people, distorts your roadmap, and quietly raises your costs while your price stays fixed. Most founders count the revenue and forget to price the drag.

So compute the expected value honestly. Estimate the probability that this client behaves well, the probability they behave badly, and what each outcome is worth after counting senior hours, delayed work for other customers, and the chance of a messy exit. If the difficult case is likely, the headline number is fiction. Treat the client as a rational actor optimizing for themselves: they will push scope, pay slowly, and demand attention for as long as it costs them nothing to do so.

The remedy is to make cooperation their best strategy. Require a paid discovery phase, milestone-based payments with a deposit up front, a written change-order process where extra scope carries extra price, and a clean termination clause. A client who accepts these has revealed they are manageable. A client who refuses has answered your question for free.

Next move: this week, send the proposal with those terms, priced about 20 percent above your normal rate to cover the difficulty premium, and let their reaction decide.

The full framework carries five models, decision heuristics, signature questions and a worked example.

Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.

Download this framework
$4.99
4 for $14.99 · 10 for $29.99
Save up to 40% with a bundle

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Inspired by the documented thinking of John von Neumann. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.

Related frameworks

Other scientist & thinkers