`cleverhack.com`

`Anthropic’s Claude Plays Pokémon!`

February 2025 (Updated November 2025)

This isn’t just child’s play. While being very cool, the significance is that Claude is using reasoning plus some computer vision and some other tooling to play a game *Claude has not been trained on*. This. Is. Huge.

Instead of a game, think of the other ways — AI agents, workflows, apps — where we can harness reasoning to help us perform a series of ongoing actions.

Watch the real-time gameplay and Claude’s reasoning in action here → twitch.tv/claudeplayspokemon

November 2025 update: Guess what? Claude got an upgrade. Now you can watch Anthropic's new Claude Opus 4.5 playing Pokémon.

`Menu`	`About The Author`	`More AI Writing`
`⇒ HOME` `⇒ ABOUT`	`Joy Larkin is a technologist in Silicon Valley. She likes robots and is excited for Superintelligence. LinkedIn: /in/joylarkin ◦◦◦ Twitter: @joy`	`The challenges of building agentic AI systems for business use cases`

`Menu`

`About The Author`

`More AI Writing`

⇒ HOME

⇒ ABOUT

Joy Larkin is a technologist in Silicon Valley. She likes robots and is excited for Superintelligence. LinkedIn: /in/joylarkin ◦◦◦ Twitter: @joy

The challenges of building agentic AI systems for business use cases