AI Safety Forum Australia

Program

7-8 November 2024Sydney Knowledge Hub, The University of Sydney, Sydney, Australia

Forum Topics

Some Questions We'll Explore

Technical AI Safety

What are the central technical challenges in making AI systems safe, and where is progress being made?

AI Governance

How should AI systems be governed, and what can Australia learn from international approaches?

Australia's Role

What are Australia's strengths in AI safety, and how can they be brought to bear?

Risk Assessment

How do we identify and assess risks from AI systems when the science itself is still evolving?

Evaluations & Testing

How do we measure what AI systems can do, and what counts as a meaningful safety evaluation?

Cross-Sector Dialogue

How can researchers, policymakers, and practitioners actually work together on AI safety?

2024 HIGHLIGHTS

Watch 2024 Sessions

Introduction to the Forum - Liam Carroll

State of AI - Tiberio Caetano

Technical AI Safety - Daniel Murfet

State of AI Governance - Kimberlee Weatherall

Red-Teaming for Generative AI - Hoda Heidari

Accelerating AI Safety Talent - Ryan Kidd

Frontier AI Safety Governance - Seth Lazar

ASI Safety via AIXI - Marcus Hutter