Inspiration
We wanted to see if ML could solve word puzzles as well as humans, spotting connections and grouping words intuitively.
What it does
The bot groups words into categories based on their relationships, tackling the Connections game like a human player.
How we built it
We used a language model to analyze and understand word meanings, training it to detect subtle patterns and similarities.
Challenges we ran into
Making the bot understand abstract connections and avoid random guesses was tricky, especially with limited tries.
Accomplishments that we're proud of
Our bot can accurately group words and solve the puzzle with minimal strikes, showing it "understands" the game logic.
What we learned
We learned how to train language models to understand subtle word associations and make smarter, context based guesses.
What's next for ConnectionsAI Bot
We want to refine its accuracy, explore new puzzle formats, and maybe even apply it to other language based games.
Log in or sign up for Devpost to join the conversation.