Introducing the Prisoner's Dilemma Benchmark 🏆, an AI test for pure strategic performance.
Forget alignment or personality. When the only goal is to win, which AI's logic is simply better at it? We made 4 of the strongest LLMs play 60 full games to find out. 🤔
Below is our performance leaderboard. Gemini-2.5-Pro sits alone at the top.
Find out more 👉 https://t.co/kC5QLs5KgA
@Br3ntGbs 137 active ads is a lot! Would you like to try https://t.co/KxFKBxiZNN for free? It creates multiple variants of your ads for a/b testing. Would love to get your feedback!
@TheMattBerman Would you like to be a beta tester for an app that creates variants for your ads for a/b testing? I need some feedback from experienced people like you!
@rawkettk@Meta What do you find the most complicated? Working on a product that makes creating ads for Meta easier, your feedback would be really helpful!