zlacker

[return to "Advancing AI Benchmarking with Game Arena"]
1. bennyf+Nh[view] [source] 2026-02-02 19:15:23
>>salkah+(OP)
Wow. I'm generally in the AI maximalist camp. But adding Werewolf feels dangerous to me. Anyone who's played knows lying, deceipt, and manipulation is often key to winning. We really want models climbing this benchmark?
◧◩
2. bileka+9k[view] [source] 2026-02-02 19:28:52
>>bennyf+Nh
Good question, but who's going to stop them?

AI already has a very creative imagination for role play so this just adds extra to their arsenal.

[go to top]