I was inspired by <a href="https://news.ycombinator.com/item?id=43586380">https://news.ycombinator.com/item?id=43586380</a> to simulate the reality TV show "The Traitors" using open-source LLMs. I used all open source via either groq or locally hosted on llama-server (llama.cpp)<p>Watching the games unfold is pretty entertaining, even when the very small models lose track of the plot.(like a outmatched severely quantized phi4)<p>I plan to improve the visualizations over time.<p>The repo is here: <a href="https://github.com/michaelgiba/the-traitors">https://github.com/michaelgiba/the-traitors</a><p>One game's visualization is here: <a href="https://michaelgiba.github.io/the-traitors/results/traitors/q4t20jws/plomp.html" rel="nofollow">https://michaelgiba.github.io/the-traitors/results/traitors/...</a>