The George Soros
Framework
Reflexivity & Radical Uncertainty
George Soros built capital over decades by applying specific, repeatable mental models to uncertainty. George Soros's investing thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The reflexivity & radical uncertainty framework distils George Soros'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 George Soros made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with George Soros's distinctive patterns rather than a default model voice.
A glimpse of George Soros's thinking.
Markets are not efficient mechanisms that tend toward equilibrium—they are reflexive systems where participants' biased perceptions influence the situations they're trying to understand, creating boom-bust cycles. Human fallibility is not a bug in the system; it's the feature that creates opportunity for those who recognize and exploit these recursive feedback loops.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
Where is the prevailing bias creating its own temporary reality?
4 more questions in George Soros's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics George Soros 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.
- ✦Core philosophy: 2–3 sentences grounded in George Soros'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 George Soros, 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
- →george-soros.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →george-soros-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Don't treat this as a yes-or-no on revenue. Treat it as a bet on a loop. A large, difficult client changes the company it is buying. Its demands set your roadmap, its payment terms set your cash, and its pressure on your team sets who stays. Within a year the business will have reshaped itself around that client, and the founder's belief that "we'll absorb this and stay in control" is exactly the sort of flawed perception that feeds the cycle. Concentration works in a boom: the client's growth lifts your numbers, the numbers lift your confidence, the confidence justifies hiring for the client, and the dependence deepens. It also fails in a bust, because the client holds the leverage and can reprice you the moment you cannot walk away.
My position: take it only if you can still say no after the deal is signed. That means the client stays under roughly 30 percent of revenue, you bill monthly with a deposit up front, and the contract caps custom work. If the only way to win it is to give up those three things, the difficulty is the price of dependence, and it is too high.
Next move this week: put the client's real numbers into a model, including the extra support hours and the two people you will need to hire. Then ask the client to agree to a 90-day paid pilot with a defined exit. How they respond to that request will tell you everything about what the relationship will become.
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.
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 George Soros. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.