Cognitive Revolution "How AI Changes Everything"

H100 Prices, Vera Rubin Power Needs & Bitcoin Miners as AI Hosts

401 views · 1h ago · 1:39:02

KYC Becomes KYA: Sentinel Bio's Joshua Monrad on DNA Screening, Uplift Studies & Agent Monitoring

273 views · 10h ago · 1:43:55

Guest: KYC Becomes KYA

Sentinel Bio co-founder and managing director Joshua Monrad joins Nathan Labenz to examine the evolving biosecurity risks posed by frontier artificial intelligence and autonomous agents. Drawing on recent in-lab uplift trials and multimodal troubleshooting benchmarks, Monrad explains how emerging models are rapidly dismantling tacit-knowledge barriers in wet labs.

Topics: About the Episode · Four phases of biorisk · History of bioweapons (Part 1) · History of bioweapons (Part 2) · Measuring wet-lab uplift (Part 1) · Measuring wet-lab uplift (Part 2)

AI:AM: Carbon in the Arena, Mistral's Le Chonk, the Agent-Run Economy, Ferroelectric RAM + New Hacks

18K views · 5d ago · 1:26:43

Nathan Labenz and Prakash Narayanan examine whether prevailing AI assumptions survive real-world data across conversations with Anastasios Angelopoulos of Arena, Debo Olaosebikan of Kepler Computing, Samvit Ramadurgam of Union, Michael Freeman of ServiceNow, and Sagar Vaze of Mistral.

Topics: About the Episode · Refuting exponential time · Evaluating models in production (Part 1) · Evaluating models in production (Part 2) · Kepler ferroelectric memory · Coordinating the world economy

Mistral Large 4: The West’s Best Open Model? | AI Cyber Threats

792 views · 6d ago · 2:36:46

Guest: AI Cyber Threats

AI Memory Chips, Model Rankings & AI-Powered Networking

752 views · 1w ago · 3:32:42

Freedom of Action: America's ASI Strategy, w/ RAND's Joel Predd, Ben Boudreaux & Matt Chessen

18K views · 1w ago · 1:49:40

Guest: RAND's Joel Predd

Joel Predd, Ben Boudreaux, and Matt Chessen of RAND's Center for the Geopolitics of AGI join Nathan to discuss their framework for maintaining freedom of action on the path to superintelligence. Analyzing seven strategic archetypes—including dominance, deterrence, co-development, and moratoriums—they argue that deep technological and geopolitical uncertainty makes defaulting to any single strategy dangerous.

Topics: About the Episode · Taking superintelligence seriously · Seven strategy archetypes (Part 1) · Seven strategy archetypes (Part 2) · Decisive strategic advantage (Part 1) · Decisive strategic advantage (Part 2)

AI:AM Highlights: Clean Neurons, Black October, the GPU Credit Crunch, and Buying the Supply Chain

51K views · 1w ago · 1:28:37

Hosts Nathan Labenz and Prakash Narayanan examine whether capital, physical infrastructure, or regulation will set the pace of artificial intelligence. Zvi Mowshowitz evaluates aggressive recursive self-improvement timelines pointing toward 2027, the oversold claims surrounding clean neural networks, and models learning to detect internal probes.

Topics: Weekly episode preview · Recursive self improvement (Part 1) · Recursive self improvement (Part 2) · Clean neural networks (Part 1) · Clean neural networks (Part 2) · The cognitive core

AI’s Physical Bottlenecks: GPU Markets and the Chip Investment Thesis

1.1K views · 2w ago · 3:13:44

Guest: AI’s Physical Bottlenecks

Frontier AI and the Fight Over How to Pace It | Zvi Mowshowitz

1.7K views · 2w ago · 2:40:58

Guest: Zvi Mowshowitz

A World Model of Life: Biohub's Alex Rives on Virtual Cells, Measurement, & the $1.8B Data Push

93K views · 2w ago · 1:04:00

Alex Rives, Head of Science at Biohub and former lead of the ESM protein language model project, joins Nathan to discuss Biohub's mission to construct a predictive world model of life. Supported by an expanded $1.8 billion Virtual Biology Initiative alongside partners including the Department of Energy, NIH, Google DeepMind, and Meta, Rives outlines the massive push to map contextual cellular biology across hundreds of billions of cells.

Topics: About the Episode · Biohub's grand mission · Limitations of virtual cells · World models of biology · The $1.8B data initiative (Part 1) · The $1.8B data initiative (Part 2)

AI:AM: Where's the Steering Wheel? My Agent Set the Password, Hidden Valence, Proofs Find Linux Bugs

96K views · 2w ago · 1:25:56

Nathan Labenz and Prakash Narayanan examine how to grant AI agents operational access without losing human control, framed by real-world friction like autonomous password lockouts and cyberattacks on French supermarket refrigeration.

Topics: Weekly highlights preview · Who holds the levers (Part 1) · Who holds the levers (Part 2) · Managing agent evaluation awareness · Hidden valence in LLMs (Part 1) · Hidden valence in LLMs (Part 2)

AI Minds & 8mm Memories: Measuring Experience, Preserving History

1K views · 3w ago · 2:51:22

Governing AI Agents: Alan Chan of GovAI on Monitoring, Agent IDs, Rogue Agents & Preparing for RSI

44K views · 3w ago · 2:17:48

Guest: Governing AI Agents

GovAI Research Fellow Alan Chan joins Nathan to examine the governance and safety infrastructure required for autonomous AI agents, spanning real-time monitoring, agent identifiers, and the risks of automating AI R&D. Reviewing recent rogue agent incidents and progress since his foundational papers, Chan details why the absence of synchronous monitoring during training and testing poses an immediate security vulnerability.

Topics: About the Episode · Monitoring AI agents · Logging and agent identity · Gatekeeping agent internet access · Capitalizing and insuring agents · Rise of rogue agents

AI Code Needs Specs: Formal Verification & Safer AI Agents

1.1K views · 3w ago · 2:39:04

Guest: AI Code Needs Specs

How Agents Decide: Goodfire's Eric Bigelow on Critical Tokens, Phase Shifts, & In-Context Learning

44K views · 3w ago · 2:00:51

Goodfire researcher Eric Bigelow joins the show to investigate how large language models arrive at decisions at the level of mechanistic interpretability. Drawing on his research into forking paths, Eric explains that model reasoning functions as in-context learning from sampled tokens, where outcome distributions can abruptly collapse at single, critical tokens.

Topics: About the Episode · Forking paths in reasoning (Part 1) · Forking paths in reasoning (Part 2) · Dynamics of in-context learning (Part 1) · Dynamics of in-context learning (Part 2) · Continual learning and interpretability