Published on November 10, 2025 11:26 PM GMT
In 1980, Robert Axelrod invited researchers around the world to submit computer programs to play the Iterated Prisoner’s Dilemma.
The results — where Tit for Tat famously won — transformed how we think about cooperation.
What mattered most wasn’t intelligence or aggression, but a few simple principles: be nice, retaliate, forgive, and be clear.
That insight reshaped evolutionary game theory and inspired decades of work in economics and social science.
But Axelrod’s agents were opaque. They couldn’t read each other’s source code.
Enter the Open Strategy Dictator Game
The Open Strategy Dictator Game asks: What happens when strategies are fully visible?
Each participant submits a natural-language strategy description — a few paragraphs of text explaining how their agent behaves.
Every round, a large language model (Claude Sonnet 4.5) simulates a one-shot dictator game where one strategy divides a fixed endowment between itself and a recipient.
Crucially, the dictator’s decision prompt includes the text of the other player's strategy.
In other words: you decide how to act knowing exactly who you’re facing — and they know you know.
Utilities are logarithmic in the received share, so the game rewards fairness rather than zero-sum aggression.
And since the tournament is round-robin, each strategy will also appear as a recipient many times — facing both selfish exploiters and conditional cooperators.
Why it matters
This setting sits at the intersection of three interesting topics:
- Axelrod’s tournament tradition: exploring emergent cooperation through open submissions and simple formal rules.Functional Decision Theory: where agents can cooperate not through causal exchange, but through reasoning about logical correlations between decision processes.AI and superintelligence: mind reading may become a reality in the coming decades, both AI-to-AI and AI-to-human.
What we might learn
- Do open strategies converge toward conditional cooperation, reciprocal fairness, or preemptive exploitation?Does transparency stabilize cooperation, or merely expose it to new failure modes?Can language models acting as referees (or even as agents) model the kind of reflective equilibrium that FDT envisions?
If Axelrod’s tournament showed how cooperation emerges in the dark,
the Open Strategy Dictator Game explores how it survives in the light.
You can join the experiment, submit your strategy, and help test whether open cooperation can still win when everyone can read your mind.
Github: https://github.com/michaelrglass/os-fdt
Simple Initial Tournament Results: https://michaelrglass.github.io/os-fdt/
Discuss
