Semantris is a set of word associations games powered by machine learning developed at Google. The games are a fun and engaging way of introducing people to the growing capabilities of Google technologies to understand language. By training on billions of conversations on the internet, the AI has learned how to predict which words, phrases, and even sentences might come next in a conversation.

The two games, Blocks and Arcade, use the same AI, but provide different ways of interacting with it. When you enter a clue, the AI looks at all the words in play and chooses the ones it thinks are most related.

  • Arcade challenges you to quickly come up with word association clues that the AI can understand. It’s a race to think and type as fast as you can before a growing list of words reaches the top of the screen.
  • Blocks is turn based, not time based. So you can take as long as you’d like to come up with different types of clues and see which ones the game understands best. Try using slang, lists of examples, pop culture references, and even full sentences.

Semantris launched initially as an online experience, but it has also been shown as an installation at live events.

Concept, Programming, Production: Ben Pietrzak, RJ Mical, Steve Pucci, Maria Voitovich (Mind Games)
UX, Copy, Art Direction: Catherine McCurry
Production: Mo Adeleye, Diana Huang
Design & Art Direction: Tomomi Sohn
Music: Connor Moore

AI Experiments
Google AI
Tech Crunch
The Verge