
LLM Let's Play - Fire Emblem
Agent gameplay harness: mGBA state in, tactical context to the model, controller actions back, dashboard for humans.

(Click to skip) →

Agent gameplay harness: mGBA state in, tactical context to the model, controller actions back, dashboard for humans.


TEE-backed verifiable randomness infrastructure for giveaways and gachapon systems without on-chain costs.




600-game benchmark across six hosted LLMs for measuring deception, lie detection, and instruction compliance in a hidden-information card game.
“Honesty prompts reduced lying, but also reduced challenges and made remaining lies more successful.”