Davidad Dalrymple: Towards Provably Safe AI

The Gradient Podcast by Daniel Bashir

Sep 5, 202480:50Technology

Episode 137 I spoke with Davidad Dalrymple about: * His perspectives on AI risk * ARIA (the UK’s Advanced Research and Invention Agency) and its Safeguarded AI Programme Enjoy—and let me know what you think! Davidad is a...

Related Episodes

Continue listening to more episodes from The Gradient Podcast.

2025 in AI, with Nathan Benaich

Jan 22, 2026 - 61:15

Episode 144 Happy New Year! This is one of my favorite episodes of the year — for the fourth time, Nathan...

Iason Gabriel: Value Alignment and the Ethics of Advanced AI Systems

Nov 26, 2025 - 58:39

Episode 143 I spoke with Iason Gabriel about: * Value alignment * Technology and worldmaking * How AI sys...

2024 in AI, with Nathan Benaich

Dec 26, 2024 - 108:43

Episode 142 Happy holidays! This is one of my favorite episodes of the year — for the third time, Nathan...

Philip Goff: Panpsychism as a Theory of Consciousness

Dec 12, 2024 - 60:04

Episode 141 I spoke with Professor Philip Goff about: * What a “post-Galilean” science of consciousness l...

Some Changes at The Gradient

Nov 21, 2024 - 34:25

Hi everyone! If you’re a new subscriber or listener, welcome. If you’re not new, you’ve probably noticed...

Jacob Andreas: Language, Grounding, and World Models

Oct 10, 2024 - 112:43

Episode 140 I spoke with Professor Jacob Andreas about: * Language and the world * World models * How he’...

Evan Ratliff: Our Future with Voice Agents

Sep 26, 2024 - 79:59

Episode 139 I spoke with Evan Ratliff about: * Shell Game , Evan’s new podcast, where he creates an AI vo...

Meredith Ringel Morris: Generative AI's HCI Moment

Sep 12, 2024 - 97:45

Episode 138 I spoke with Meredith Morris about: * The intersection of AI and HCI and why we need more cro...