Mario Gibney

AI Safety Thurs­day: Risks Emerg­ing from Agent Swarms

AI Policy Tues­day: AI Safety in Healthcare

AI Policy Tues­day: Reg­u­lat­ing AI Agents—Les­sons from the EU AI Act

AI Safety Thurs­day: Im­pli­ca­tions of Con­tinual Learn­ing in LLM Agents

“The World After AGI” Discussion

AI Policy Tues­day: Reg­u­lat­ing Catas­trophic AI Risk Through Li­a­bil­ity Insurance

Beyond Ad­ver­sar­ial Ro­bust­ness—Re­think­ing So­ciopoli­ti­cal Safety in AI Systems

Emer­gent Misal­ign­ment from Re­ward Hacking

AI Safety Thurs­days: Why At­tack­ers Are Win­ning and What We Can Do About It

AI Safety Thurs­day: Agen­tic Bug De­tec­tion—Progress and Deployment

Weird AI Wed­nes­day: The Rise of Par­a­sitic AI

AI Policy Tues­day: Ver­ifi­ca­tion Mechanisms for Global AI Governance

AI Policy Tues­day: The Con­cept of Poli­ti­cal Space and AI Safety

AI Policy Tues­day: The US AI Ac­tion Plan

AI Safety Thurs­days: The In­tel­li­gence Curse

AI Safety Thurs­days: Self-Other Over­lap—Fol­low Up

Apart Re­search Hackathon: AI Safety x Physics Grand Challenge

AI Safety Thurs­days: Agen­tic Misal­ign­ment: How LLMs could be in­sider threats

AI Policy Tues­days: The Fu­ture of Cana­dian AI Governance

AI Policy Tues­days: Tort Law and Fron­tier AI Governance