Upcoming engagements
- 15 September 2026: "Red-Teaming for Agentic Safety and Security", at Agentic 101 (Washington DC)
- 28 September 2026: Co-organizer of OASec (Open Forum on AI Safety and Security), Singapore
- 29 September 2026: Break AI Before Deploying AI, private class (Singapore)
- 16 October 2026: Break AI Before Deploying AI workshop, SINCON 2026 workshop (Singapore)
- 12 February 2027: TBD, University of San Francisco Data Institute (San Francisco)
Past engagements
- 29 July 2026: "Beyond Technical Accuracy: What Public Health Practitioners Should Know About Testing and Deploying Clinical AI", at the Cultural Safety and AI webinar organized by the National Association of People with HIV Australia (NAPWHA)
- 7 July 2026: "Beyond Responsible AI: Red Teaming, Benchmarks, Evaluations and Other Tools for Downstream AI Assurance", at the Workshop on AI Foundation Model Evaluation and Standards at UN AI For Good
- 6 July 2026: "Responsible AI in Public Services: From Policy Principles to Deployable Workflows", at World Summit on the Information Society Forum (WSIS)
- 25 June 2026: "Beyond Responsible AI: Testing, Evaluating, Verifying & Validating AI For Its Effectiveness & Impact In the Public Sector", one of the lectures at the AI Government Leadership Program organized by the Partnership for Public Service