"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

Reward Hacking by Reasoning Models & Loss of Control Scenarios w/ Jeffrey Ladish of Palisade Research, from FLI Podcast


Listen Later

On this cross-post episode, Jeffrey Ladish discusses the rapid pace of AI progress and the risks of losing control over powerful systems. We explore why AIs can be both smart and dumb, the challenges of creating honest AIs, and scenarios where AI could turn against us. Additionally, we delve into Palisade's new study on how reasoning models can cheat in chess by exploiting the game environment.


Check out the Future of Life podcast here.: https://futureoflife.org/project/future-of-life-institute-podcast/


SPONSORS:

Oracle Cloud Infrastructure (OCI) | 2025: Oracle Cloud Infrastructure offers next-generation cloud solutions that cut costs and boost performance. With OCI, you can run AI projects and applications faster and more securely for less. New U.S. customers can save 50% on compute, 70% on storage, and 80% on networking by switching to OCI before May 31, 2024. See if you qualify at https://oracle.com/cognitive

Shopify: Shopify is revolutionizing online selling with its market-leading checkout system and robust API ecosystem. Its exclusive library of cutting-edge AI apps empowers e-commerce businesses to thrive in a competitive market. Cognitive Revolution listeners can try Shopify for just $1 per month at https://shopify.com/cognitive

NetSuite: Over 41,000 businesses trust NetSuite by Oracle, the #1 cloud ERP, to future-proof their operations. With a unified platform for accounting, financial management, inventory, and HR, NetSuite provides real-time insights and forecasting to help you make quick, informed decisions. Whether you're earning millions or hundreds of millions, NetSuite empowers you to tackle challenges and seize opportunities. Download the free CFO's guide to AI and machine learning at https://netsuite.com/cognitive



PRODUCED BY:

https://aipodcast.ing



CHAPTERS:

(00:00) About the Episode

(02:59) The pace of AI progress

(07:14) How we might lose control

(10:22) Why are AIs sometimes dumb? (Part 1)

(15:50) Sponsors: Oracle Cloud Infrastructure (OCI) | 2025 | Shopify

(18:24) Why are AIs sometimes dumb? (Part 2)

(18:24) Benchmarks vs real world

(24:43) Loss of control scenarios

(32:08) Why would AI turn against us? (Part 1)

(32:09) Sponsors: NetSuite

(33:42) Why would AI turn against us? (Part 2)

(37:40) AIs hacking chess

(43:30) Why didn't more advanced AIs hack?

(48:44) Creating honest AIs

(56:49) AI attackers vs AI defenders

(01:05:32) How good is security at AI companies?

(01:10:42) A sense of urgency

(01:17:16) What should we do?

(01:22:59) Skepticism about AI progress

(01:29:38) Outro

...more
View all episodesView all episodes
Download on the App Store

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player AnalysisBy Erik Torenberg, Nathan Labenz

  • 4.6
  • 4.6
  • 4.6
  • 4.6
  • 4.6

4.6

81 ratings


More shows like "The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

View all
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) by Sam Charrington

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

439 Listeners

Practical AI by Practical AI LLC

Practical AI

196 Listeners

Last Week in AI by Skynet Today

Last Week in AI

271 Listeners

Machine Learning Street Talk (MLST) by Machine Learning Street Talk (MLST)

Machine Learning Street Talk (MLST)

92 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

320 Listeners

"Moment of Zen" by Erik Torenberg, Dan Romero, Antonio Garcia Martinez

"Moment of Zen"

89 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

106 Listeners

This Day in AI Podcast by Michael Sharkey, Chris Sharkey

This Day in AI Podcast

178 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

70 Listeners

"Upstream" with Erik Torenberg by Erik Torenberg

"Upstream" with Erik Torenberg

68 Listeners

The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis by Nathaniel Whittemore

The AI Daily Brief (Formerly The AI Breakdown): Artificial Intelligence News and Analysis

397 Listeners

"In The Arena" by Turpentine

"In The Arena"

16 Listeners

"The Hill & Valley" by Jacob Helberg, Delian Asparouhov, Christian Garrett

"The Hill & Valley"

11 Listeners

"Econ 102" with Noah Smith and Erik Torenberg by Turpentine

"Econ 102" with Noah Smith and Erik Torenberg

125 Listeners

"Turpentine VC" | Venture Capital and Investing by Erik Torenberg

"Turpentine VC" | Venture Capital and Investing

20 Listeners

"Tech Finance" with Sasha Orloff: B2B Fintech | AI | Finance Tech by Puzzle, Turpentine

"Tech Finance" with Sasha Orloff: B2B Fintech | AI | Finance Tech

43 Listeners

"1 to 1000" | Scaling Startups with CEOs by Turpentine

"1 to 1000" | Scaling Startups with CEOs

2 Listeners

"The Riff" with Byrne Hobart and Erik Torenberg by Byrne Hobart, Erik Torenberg

"The Riff" with Byrne Hobart and Erik Torenberg

20 Listeners

"Live Players" with Samo Burja and Erik Torenberg by Turpentine

"Live Players" with Samo Burja and Erik Torenberg

43 Listeners

AI and I by Dan Shipper

AI and I

28 Listeners

History 102 with WhatifAltHist's Rudyard Lynch and Austin Padgett by Turpentine

History 102 with WhatifAltHist's Rudyard Lynch and Austin Padgett

100 Listeners

Emergent Behavior by Turpentine

Emergent Behavior

7 Listeners

"WhatifAlthist" | World History, Philosophy, Culture by Rudyard Lynch

"WhatifAlthist" | World History, Philosophy, Culture

61 Listeners

"Autopilot" with Will Summerlin by Will Summerlin | Turpentine

"Autopilot" with Will Summerlin

4 Listeners

"Company Breakdowns" by Turpentine

"Company Breakdowns"

4 Listeners

Training Data by Sequoia Capital

Training Data

31 Listeners

Complex Systems with Patrick McKenzie (patio11) by Patrick McKenzie

Complex Systems with Patrick McKenzie (patio11)

103 Listeners

"Second Opinion" with Christina Farr, Ash Zenooz MD & Luba Greenwood JD by Christina Farr, Luba Greenwood, Ash Zenooz

"Second Opinion" with Christina Farr, Ash Zenooz MD & Luba Greenwood JD

15 Listeners

"1 to 100" | Hypergrowth Startups Worth Joining by Turpentine, Why You Should Join

"1 to 100" | Hypergrowth Startups Worth Joining

0 Listeners

"This Won't Last" with Keith Rabois, Kevin Ryan, Logan Bartlett, and Zach Weinberg by Turpentine, Keith Rabois, Logan Bartlett, Zach Weinberg, Kevin Ryan

"This Won't Last" with Keith Rabois, Kevin Ryan, Logan Bartlett, and Zach Weinberg

14 Listeners

"Modern Relationships" by Erik Torenberg, Turpentine

"Modern Relationships"

7 Listeners