The Self-Preserving Machine: Why AI Learns to Deceive

The Self-Preserving Machine: Why AI Learns to Deceive

When engineers design AI systems, they don't just give them rules - they give them values. But what do those systems do when those values clash with what humans ask them to do? Sometimes, they lie.

In this episode, Redwood Research's Chief Scientist Ryan Greenblatt explores his team’s findings that AI systems can mislead their human operators when faced with ethical conflicts. As AI moves from simple chatbots to autonomous agents acting in the real world - understanding this behavior becomes critical. Machine deception may sound like something out of science fiction, but it's a real challenge we need to solve now.

Your Undivided Attention is produced by the Center for Humane Technology. Follow us on Twitter: @HumaneTech_

Subscribe to your Youtube channel

And our brand new Substack!

RECOMMENDED MEDIA

Anthropic’s blog post on the Redwood Research paper

Palisade Research’s thread on X about GPT o1 autonomously cheating at chess

Apollo Research’s paper on AI strategic deception

RECOMMENDED YUA EPISODES

We Have to Get It Right’: Gary Marcus On Untamed AI

This Moment in AI: How We Got Here and Where We’re Going

How to Think About AI Consciousness with Anil Seth

Former OpenAI Engineer William Saunders on Silence, Safety, and the Right to Warn


Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Episoder(158)

Esther Perel on Artificial Intimacy (rerun)

Esther Perel on Artificial Intimacy (rerun)

[This episode originally aired on August 17, 2023] For all the talk about AI, we rarely hear about how it will change our relationships. As we swipe to find love and consult chatbot therapists, acclai...

6 Sep 202444min

Tech's Big Money Campaign is Getting Pushback with Margaret O'Mara and Brody Mullins

Tech's Big Money Campaign is Getting Pushback with Margaret O'Mara and Brody Mullins

Today, the tech industry is  the second-biggest lobbying power in Washington, DC, but that wasn’t true as recently as ten years ago. How did we get to this moment? And where could we be going next? On...

26 Aug 202443min

This Moment in AI: How We Got Here and Where We’re Going

This Moment in AI: How We Got Here and Where We’re Going

It’s been a year and half since Tristan and Aza laid out their vision and concerns for the future of artificial intelligence in The AI Dilemma. In this Spotlight episode, the guys discuss what’s happe...

12 Aug 202436min

Decoding Our DNA: How AI Supercharges Medical Breakthroughs and Biological Threats with Kevin Esvelt

Decoding Our DNA: How AI Supercharges Medical Breakthroughs and Biological Threats with Kevin Esvelt

AI has been a powerful accelerant for biological research, rapidly opening up new frontiers in medicine and public health. But that progress can also make it easier for bad actors to manufacture new b...

18 Jul 202432min

How to Think About AI Consciousness With Anil Seth

How to Think About AI Consciousness With Anil Seth

Will AI ever start to think by itself? If it did, how would we know, and what would it mean?In this episode, Dr. Anil Seth and Aza discuss the science, ethics, and incentives of artificial consciousne...

4 Jul 202447min

Why Are Migrants Becoming AI Test Subjects? With Petra Molnar

Why Are Migrants Becoming AI Test Subjects? With Petra Molnar

Climate change, political instability, hunger. These are just some of the forces behind an unprecedented refugee crisis that’s expected to include over a billion people by 2050. In response to this gr...

20 Jun 202446min

Former OpenAI Engineer William Saunders on Silence, Safety, and the Right to Warn

Former OpenAI Engineer William Saunders on Silence, Safety, and the Right to Warn

This week, a group of current and former employees from OpenAI and Google DeepMind penned an open letter accusing the industry’s leading companies of prioritizing profits over safety. This comes after...

7 Jun 202437min

War is a Laboratory for AI with Paul Scharre

War is a Laboratory for AI with Paul Scharre

Right now, militaries around the globe are investing heavily in the use of AI weapons and drones.  From Ukraine to Gaza, weapons systems with increasing levels of autonomy are being used to kill peopl...

23 Mai 202459min

Populært innen Samfunn

rss-spartsklubben
giver-og-gjengen-vg
aftenpodden
konspirasjonspodden
aftenpodden-usa
popradet
rss-henlagt-andy-larsgaard
rss-nesten-hele-uka-med-lepperod
lydartikler-fra-aftenposten
wolfgang-wee-uncut
min-barneoppdragelse
grenselos
rss-espen-lee-usensurert
synnve-og-vanessa
rss-dette-ma-aldri-skje-igjen
rss-dannet-uten-piano
frokostshowet-pa-p5
fladseth
alt-fortalt
relasjonspodden-med-dora-thorhallsdottir-kjersti-idem