Building Safe AI - MIT AI Alignment's Riya Tyagi and Gatlen Culp

About this episode

The episode discusses AI safety with Riya Tyagi and Gatlen Culp from MIT AI Alignment, exploring risks and collaborative efforts for a safer future.

Riya and Gatlen are board members of MIT AI Alignment, an organization focused on reducing risks from advanced artificial intelligence. Join us as we map the AI safety landscape, define key risks, examine generational perspectives, and explore how we can work together to build a safer future for humanity. Hosted by Nabil Laoudji. See below for episode links, chapters, and our socials. 🙏🙌 Episode Links: MIT AI Alignment Cambridge Boston Alignment Initiative (CBAI) Riya's LinkedIn Gatlen's LinkedIn Gatlen's Projects Slaughterbots x Future of Life Institute Track II Diplomacy Tegmark AI Safety Group "Nexus" by Yuval Noah Harari RAND Institute BlueDot Impact "If Anyone Builds It, Everyone Dies" by Eliezer Yudkowsky and Nate Soares Chapters: (00:00) - Preview & Intro (01:48) - What Is MAIA? (02:47) - Why AI Safety? (09:26) - Trends in AI Safety Interest (12:46) - AI Safety Techniques: MechInterp & Beyond (17:15) - Model Situational Awareness (20:58) - Hybrid, Mixture of Experts Models (24:40) - Decomposing a Model & Parallels with Human Brains (29:00) - Private Capital for Safety Research (32:23) - Frontier Lab Mentorship Programs (34:14) - Policy Perspectives & China Competition…

People in this episode

Host: Nabil Laoudji

Guests: Riya Tyagi, Gatlen Culp

Topics covered

• AI safety
• artificial intelligence
• risk reduction
• collaboration
• policy perspectives
• generational attitudes

Keywords

• AI alignment
• safety techniques
• international collaboration
• policy
• AI threats
• mentorship programs
• generational perspectives

Mentioned in this episode

Organizations: MIT AI Alignment, Cambridge Boston Alignment Initiative, Future of Life Institute, RAND Institute

Books & works: Nexus, If Anyone Builds It, Everyone Dies

More episodes of Discovery Engines – with Nabil

• Democratizing AI for Biology | Discovery Engines · June 11, 2026 · 1h 7m
• Building an AI-Driven Autonomous Lab for Life Science R&D | Discovery Engines · March 30, 2026 · 1h 39m
• AI for Physics Discovery - Jesse Thaler of NSF's IAIFI, MIT's Center for Theoretical Physics · August 6, 2025 · 59 min
• Universal Lab Automation - Rick Wierenga of PyLabRobot · June 19, 2025 · 1h 1m
• Breaking Into AI for Science - Alishba Imran of UC Berkeley BAIR, Arc Institute, CZ Biohub, Voltx · May 7, 2025 · 1h 6m
• Unleashing Scientific Data - Nicholas Larus-Stone of Sphinx Bio, Bits in Bio · April 23, 2025 · 1h 6m