LessWrong (30+ Karma)

“How training-gamers might function (and win)” by Vivek Hebbar


Listen Later

In this post I lay out a concrete vision of how reward-seekers and schemers might function. I describe the relationship between higher level goals, explicit reasoning, and learned heuristics. I explain why I expect reward-seekers and schemers to dominate proxy-aligned models given sufficiently rich training environments (and sufficient reasoning ability).

A key point is that explicit reward seekers can still contain large quantities of learned heuristics (context-specific drives). By viewing these drives as instrumental and having good instincts for when to trust them, a reward seeker can capture the benefits of both instinctive adaptation and explicit reasoning without paying much of a speed penalty.

Core claims

  1. To get high reward, models must learn context-specific heuristics which are not derivable by reasoning from the goal of reward maximization.[1]
  2. It is also true that thinking explicitly about reward is sometimes a waste of time and punished by speed penalties.
  3. It [...]

---

Outline:

(00:52) Core claims

(01:52) Characterizing reward-seekers

(06:59) When will models think about reward?

(10:12) What I expect schemers to look like

(12:43) What will terminal reward seekers do off-distribution?

(13:24) What factors affect the likelihood of scheming and/or terminal reward seeking?

(14:09) What about CoT models?

(14:42) Relationship of subgoals to their superior goals

(16:19) A story about goal reflection

(18:54) Thoughts on compression

(21:30) Appendix: Distribution over worlds

(24:44) Canary string

(25:01) Acknowledgements

The original text contained 6 footnotes which were omitted from this narration.

---

First published:

April 11th, 2025

Source:

https://www.lesswrong.com/posts/ntDA4Q7BaYhWPgzuq/reward-seekers

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

...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

26,368 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,397 Listeners

The Peter Attia Drive by Peter Attia, MD

The Peter Attia Drive

7,808 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

4,108 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

1,451 Listeners

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

All-In with Chamath, Jason, Sacks & Friedberg

8,774 Listeners

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

Machine Learning Street Talk (MLST)

89 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

354 Listeners

Hard Fork by The New York Times

Hard Fork

5,363 Listeners

The Ezra Klein Show by New York Times Opinion

The Ezra Klein Show

15,028 Listeners

Moonshots with Peter Diamandis by PHD Ventures

Moonshots with Peter Diamandis

461 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

127 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

65 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

432 Listeners