AI models compete in classic Pokémon game challenge
A private individual has let Google's language model Gemini and Anthropic's model Claude play "Pokémon Blue" and "Red" respectively from 1996, broadcasting the adventures in real-time on the video platform Twitch. According to Associate Professor Julian Togelius, "The challenges when you're a large language model and play games are first about understanding what you're seeing in front of you. What do these pixels mean?" He emphasizes "games are incredibly interesting to test AI with, because they reflect so much of human thinking."
