APR Ep01: Intro — An Approach to Technical AGI Safety and Security

Alex and Thuy kick off a deep dive into Google DeepMind's comprehensive AGI safety paper by Rohin Shah and 29 co-authors.

In this episode:

• Meet the hosts — Alex (fintech PM) and Thuy (AI researcher) introduce themselves and their perspectives
• The paper — "An Approach to Technical AGI Safety and Security" (April 2025, Google DeepMind)
• Full abstract read-through — Thuy reads the abstract word-for-word, then they unpack what it means
• Four risk categories — Misuse, misalignment, mistakes, and structural risks
• Defense in depth — Why layered defenses matter, with parallels to fraud detection in fintech
• Safety cases — Structured arguments for deployment decisions

Paper link: arxiv.org/abs/2504.01849

This is episode 1 of an 8-part series covering the full paper.