On Tuesday afternoon, Anthropic launched Claude Plays Pokémon on Twitch, a livestream of Anthropic’s latest AI mannequin, Claude 3.7 Sonnet, taking part in a recreation of Pokémon Pink. It’s develop into a captivating experiment of kinds, showcasing the capabilities of at present’s AI tech and other people’s reactions to them.
AI researchers have used all kinds of video games, from Street Fighter to Pictionary, to check new fashions — typically extra for amusement than utility. However Anthropic mentioned that Pokémon proved to be a helpful benchmark for Claude 3.7 Sonnet, which may successfully “think” via the types of puzzles the sport comprises.
Like OpenAI’s o3-mini and DeepSeek’s R1, Claude 3.7 Sonnet can “motive” its manner via powerful challenges, like taking part in a online game designed for youngsters. Whereas the mannequin’s non-reasoning predecessor, Claude 3.5 Sonnet, failed the very starting of Pokémon Pink — exiting the participant’s residence in Pallet City — Claude 3.7 Sonnet managed to win three health club chief badges.
The most recent Claude nonetheless runs into hassle, although. Hours into the Twitch stream, the mannequin was deterred by a rock wall, which it couldn’t stroll via regardless of how exhausting it tried.
One Twitch person summed up the scenario this fashion: “who would win, a pc AI with hundreds of hours put into programming it, or 1 rock wall?”
Finally, Claude realized that it may navigate across the wall.
On the one hand, it’s irritating to look at Claude traverse Pokémon Pink with the velocity of a Slowpoke, reasoning via every step with excruciating contemplation. But it’s additionally oddly compelling. The left of the stream reveals Claude’s “thought course of,” whereas the appropriate reveals real-time gameplay.
At one level, Claude tried to find Professor Oak inside his laboratory, however acquired confused, as a result of there have been different NPCs within the scene.
“I discover a brand new character has appeared beneath me — a personality with black hair and what seems to be a white coat at coordinates (2, 10),” Claude wrote. “This may be Professor Oak! Let me go down and discuss to him.”
Claude then proceeded to mistakenly discuss to an NPC aside from the Professor — an NPC the mannequin had spoken with a number of instances earlier than. Among the thousand-odd individuals within the Twitch chat began to get antsy. Others, notably those that’d been watching the stream for various minutes, have been much less apprehensive.
“Guys chill,” one individual wrote within the chat. “Earlier than we exited and entered Oak’s lab like 10 instances earlier than understanding how you can transfer on.”
For longtime Twitch customers, the format of Anthropic’s stream may really feel nostalgic. Over a decade in the past, hundreds of thousands of individuals tried to play Pokémon Pink directly in a first-of-its-kind on-line social experiment known as Twitch Plays Pokémon. Every person may management the participant character through Twitch chat, leading to predictably chaotic gameplay.
Some AI researchers have cited Twitch Performs Pokémon as an inspiration for his or her work. In October 2023, Seattle-based software program engineer Peter Whidden printed a YouTube video detailing how he skilled a reinforcement studying algorithm to play Pokémon. His AI spent over 50,000 hours playing the game earlier than it realized to efficiently navigate it. One problem was that the AI most popular to admire the pixelated surroundings as a substitute of truly taking part in the sport.
AI-powered “reenactments” of Twitch Performs Pokémon like Whidden’s and Anthropic’s are entertaining, however a bit of bittersweet on the similar time. The unique stream was such a pivotal second in Twitch historical past as a result of it introduced individuals collectively in an sudden manner. Everybody was on the identical crew, working towards the purpose of getting the participant character to cease working in circles and truly progress via the sport.
In 2025, it appears we’re now not teammates, however spectators, watching an AI mannequin attempt to play a recreation many people acquired the dangle of once we have been 5 years previous. It’s an AI-motivated microcosm of a bigger pattern: Our experiences on-line are transferring from shared, communal actions to extra solitary ones.
About The Author
