LessWrong (30+ Karma)

“Training AI agents to solve hard problems could lead to Scheming” by Marius Hobbhahn, AlexMeinke


Listen Later

TLDR: We want to describe a concrete and plausible story for how AI models could become schemers. We aim to base this story on what seems like a plausible continuation of the current paradigm. Future AI models will be asked to solve hard tasks. We expect that solving hard tasks requires some sort of goal-directed, self-guided, outcome-based, online learning procedure, which we call the “science loop”, where the AI makes incremental progress toward its high-level goal. We think this “science loop” encourages goal-directedness, instrumental reasoning, instrumental goals, beyond-episode goals, operational non-myopia, and indifference to stated preferences, which we jointly call “Consequentialism”. We then argue that consequentialist agents that are situationally aware are likely to become schemers (absent countermeasures) and sketch three concrete example scenarios. We are uncertain about how hard it is to stop such agents from scheming. We can both imagine worlds where preventing scheming is incredibly [...]

---

Outline:

(01:46) Introduction

(05:31) A plausible story for how scheming could arise

(05:36) We start with an improved version of today's systems

(08:04) The AI is put into a self-supervised “Science Loop”

(11:11) Hypothesis: The “science loop” will reward Consequentialism

(14:51) Goal-directedness

(16:03) Instrumental reasoning

(17:17) Instrumental goals

(18:46) Stable beyond-episode goals

(20:00) Operational non-myopia

(21:02) Indifference to others’ preferences

(22:26) Extra: Goal drift

(23:59) Hypothesis: Consequentialism will lead to scheming

(24:16) AI will have misaligned goals

(26:35) AI will seek power

(27:15) AI will use strategic deception to achieve its goals

(32:27) Concrete scenarios for catastrophic outcomes from this setup

(32:56) Abstract hard goal leads to takeover of the US government

(38:09) AI is tasked with “building safe ASI”

(42:51) Race between superpowers leads to loss of control

(46:05) We’re very uncertain how hard it is to address scheming

(49:24) Evidence for or against scheming to look out for

(52:29) Appendix A - discussing definitions of scheming

(54:23) Appendix B - comparing with other stories of scheming

---

First published:

November 19th, 2024

Source:

https://www.lesswrong.com/posts/QqYfxeogtatKotyEC/training-ai-agents-to-solve-hard-problems-could-lead-to

---

Narrated by TYPE III AUDIO.

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

LessWrong (30+ Karma)By LessWrong


More shows like LessWrong (30+ Karma)

View all
Making Sense with Sam Harris by Sam Harris

Making Sense with Sam Harris

26,362 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,380 Listeners

The Peter Attia Drive by Peter Attia, MD

The Peter Attia Drive

7,924 Listeners

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas by Sean Carroll | Wondery

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas

4,131 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

87 Listeners

Your Undivided Attention by Tristan Harris and Aza Raskin, The Center for Humane Technology

Your Undivided Attention

1,447 Listeners

All-In with Chamath, Jason, Sacks & Friedberg by All-In Podcast, LLC

All-In with Chamath, Jason, Sacks & Friedberg

8,922 Listeners

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

Machine Learning Street Talk (MLST)

88 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

379 Listeners

Hard Fork by The New York Times

Hard Fork

5,425 Listeners

The Ezra Klein Show by New York Times Opinion

The Ezra Klein Show

15,206 Listeners

Moonshots with Peter Diamandis by PHD Ventures

Moonshots with Peter Diamandis

475 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

121 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

77 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

455 Listeners