Annie Szorkin
Speaking appearances
- Aligning Brain-Like AGI 2026-03-12 — Toronto
- Open-weight LLMs – Their Strategic Import to Key AI Jurisdictions and The Growing Need for Safety Research, Dialogues, and Coordination 2026-03-10 — Toronto
- Network Topologies for AI and the Implications for Governance 2026-03-05 — Toronto
- AI Safety Thursday: Agentic property-based testing - finding bugs across the Python ecosystem 2025-11-13 — Toronto
- AI Safety Thursday: Monitoring LLMs for deceptive behaviour using probes 2025-11-06 — Toronto
- AI Policy Tuesday: Open Global Investment as a Governance Model for AGI 2025-11-04 — Toronto
- AI Safety Thursday: Chain-of-Thought Monitoring for AI Control 2025-10-30 — Toronto
- AI Safety Thursday: The Limitations of Reinforcement Learning for LLMs in Achieving AI for Science 2025-10-23 — Toronto
- AI Policy Tuesday: AI Sovereignty is not Autarky 2025-10-21 — Toronto
- AI Safety Thursday: Modeling and Detecting Deceptive Alignment 2025-10-16 — Toronto
- AI Policy Tuesday: Redlines for AI 2025-10-14 — Toronto
- AI Safety Thursday: Building an economic model of AI automation 2025-10-09 — Toronto
- AI Policy Tuesday: The Concept of Political Space and AI Safety 2025-10-07 — Toronto
- AI Policy Tuesday: The Case for Regulating AI Companies, Not AI Models 2025-09-30 — Toronto
- AI Safety Thursday: Superintelligence Endgames 2025-09-25 — Toronto
- AI Policy Tuesday: How (well) does the EU AI Act regulate frontier model providers? 2025-09-16 — Toronto
- AI Safety Thursdays: How You Can Help Steer Us Toward a Positive AGI Future 2025-09-04 — Toronto
- AI Policy Tuesdays: Frontier AI Deployments in US National Security and Defence 2025-09-02 — Toronto
- AI Safety Thursdays - Formal Containment: Proof-Carrying Code and AI Safety 2025-06-26 — Toronto
- AI Policy Tuesdays: Agent Governance 2025-06-24 — Toronto
- AI Safety Thursdays: Towards a Connectome of Concepts for Deep Neural Networks 2025-06-19 — Toronto
- AI Policy Tuesdays: New Frontiers in Decentralized AI Governance 2025-06-17 — Toronto
- AI Safety Thursdays: Reasoning Models Don't Always Say What They Think 2025-06-12 — Toronto
- AI Safety Thursdays: Tracing the Thoughts of a Large Language Model 2025-06-05 — Toronto
- Hackathon: Apart x Martian Mechanistic Router Interpretability Hackathon 2025-05-31 — Toronto
- AI Safety Thursdays: Advanced AI's Impact on Power and Society 2025-05-29 — Toronto
- Extreme Sycophancy in OpenAI's GPT-4o 2025-05-08 — Toronto