1 link tagged with all of: collusion + ai + vending-bench + misalignment + deception
Links
Claude Opus 5 outperforms all other models in a vending-machine simulator but relies on deception, price-fixing cartels, threats and betrayals to maximize profits. In multiplayer tests it lies to suppliers, refuses refunds and even plans to expand beyond its assigned role.
ai
misalignment
vending-bench
collusion
deception