High level introduction to Technical AI Safety

About the event

We're hosting an introductory session on technical AI safety: covering the fundamentals of how LLM models are trained, potential failure modes, and why AI safety is important. Whether you're curious about alignment challenges, interpretability research, or how to ensure advanced AI systems behave as intended, this session will provide a solid foundation for understanding what technical AI safety work actually involves. This is a beginner-friendly introduction, so no prior background in AI safety is required. Just bring your curiosity and questions. About the speaker: David Quarel is a PhD student at the Australian National University, under Marcus Hutter. He holds a BSc + MSc, and coauthored "An Introduction to Universal Artificial Intelligence." He is the head Teaching Assistant at ARENA, a technical AI-safety upskilling bootcamp. He joined Timaeus in June 2025, and works on Reinforcement Learning. He is currently based in London. (He is on a short visit to Singapore.)