Lida Safety Research

LidaSim: Testing AI Policies With Persona-Based Simulations

For the AI Governance Apart Research hackathon, we created a multi-agent simulation of influential figures in AI and politics to determine which AI governance policies are more likely to be broadly supported. Specifically, we simulated group debates between ten influential figures to analyze proposals for compute governance, though the framework

Introducing Lida Safety

Lida Safety Research is a nonprofit organization for AI safety research, initially created by Linh Le and David Williams-King (hence the name Lida). We are dedicated to mitigating existential risk and gradual disempowerment, with a current focus on simulation and control techniques.