I built a simple game using Langchain and Large Language Models
Nothing more fun than having two models playing with each other.
I built a very simple game using Langchain and a few models.
It’s not a big deal, and it only took a few lines of code.
There’s a player and a host. The player has to guess a particular concept by asking questions. The host answers those questions with a simple Yes or No.
I built this game for two reasons.
First, trying new models and determining their capabilities is a great exercise. It’s an opportunity to play with different prompts and practice different techniques.
Second, it’s fun to pit different models against each other. I can try different combinations of models and see which one performs best.
While my goal was to test Llama 3, I tried a few other models. Yes, as you might have guessed, GPT-4 was the best one in my tests.
I recorded a video explaining the source code of the game. Helpful if you want to learn how to run an open-source model locally and use Langchain.