Back to explore

Jev nearly wins 100-round Iterated Prisoner's Dilemma tournament

The author entered TypeSafe's Jev model into a 100-round Iterated Prisoner's Dilemma tournament against classic game-theory strategies; Jev nearly won, showing how it behaves when trust is on the line.

I put Jev (typesafe/jev-1.13) into a 100-round Iterated Prisoner’s Dilemma tournament against classic game-theory strategies. It didn’t just understand the assignment. It nearly won the tournament. Here’s how Jev behaved when trust was on the line: 🧵 #Jev #AI #SystemOneModels

Jev nearly wins 100-round Iterated Prisoner's Dilemma tournament 1
· 2 likesOpen on X