LessWrong posts by zvi

“AI #32: Lie Detector” by Zvi


Listen Later

Can you tell if an AI is lying to you? A new paper claims that we essentially can do exactly that, at least under the right conditions. Another paper claims we can inject various sentiments into responses, getting the AI to do what we wish. Interpretability is making progress. It is exciting to think about the implications. In the short term, it would be great if we could use this to steer responses and to detect and correct hallucinations. There's a lot of potential here to explore.

In the longer term, I am more skeptical of such strategies. I do not think lie detection is a viable primary control or alignment strategy. I worry that if we go down such a path, we risk fooling ourselves, optimizing in ways that cause the techniques to stop working, and get ourselves killed. Indeed, even attempts to grab the low-hanging fruit [...]

---

Outline:

(01:30) Table of Contents

(03:47) Language Models Offer Mundane Utility

(06:31) Language Models Don’t Offer Mundane Utility

(07:44) GPT-4 Real This Time

(07:48) Fun with Image Generation

(08:04) Deepfaketown and Botpocalypse Soon

(13:32) They Took Our Jobs

(16:10) Get Involved

(17:07) Introducing

(17:52) Meta Surveillance

(23:09) In Other AI News

(24:11) Open Philanthropy Worldview Contest Awards Prizes

(24:39) First Prizes ($50k)

(24:59) Second Prizes ($37.5k)

(25:17) Third Prizes ($25k)

(27:01) Quintin Doubles Down on Twitter

(29:27) The Other Winners

(31:24) Quiet Speculations

(39:13) Open Source AI is Unsafe and Nothing Can Fix This

(46:27) The Quest for Sane Regulations

(50:38) The Week in Audio

(52:03) Rhetorical Innovation

(59:48) Eliezer Yudkowsky clarifies a recent misunderstanding about the Orthogonality Thesis (here is his full best explanation of the thesis, from Arbital).

(01:02:49) Aligning a Smarter Than Human Intelligence is Difficult

(01:12:22) People Are Worried About AI Killing Everyone

(01:12:55) Other People Are Not As Worried About AI Killing Everyone

(01:17:48) The Lighter Side

---

First published:

October 5th, 2023

Source:

https://www.lesswrong.com/posts/iDoTRmCH22PaFYL6x/ai-32-lie-detector

---

Narrated by TYPE III AUDIO.

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

LessWrong posts by zviBy zvi

  • 5
  • 5
  • 5
  • 5
  • 5

5

2 ratings


More shows like LessWrong posts by zvi

View all
Making Sense with Sam Harris by Sam Harris

Making Sense with Sam Harris

26,392 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,462 Listeners

The a16z Show by Andreessen Horowitz

The a16z Show

1,102 Listeners

Future of Life Institute Podcast by Future of Life Institute

Future of Life Institute Podcast

109 Listeners

ChinaTalk by Jordan Schneider

ChinaTalk

296 Listeners

Politix by Politix

Politix

89 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

553 Listeners

Hard Fork by The New York Times

Hard Fork

5,558 Listeners

Clearer Thinking with Spencer Greenberg by Spencer Greenberg

Clearer Thinking with Spencer Greenberg

140 Listeners

LessWrong (Curated & Popular) by LessWrong

LessWrong (Curated & Popular)

14 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

140 Listeners

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

"Econ 102" with Noah Smith and Erik Torenberg

155 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

459 Listeners

LessWrong (30+ Karma) by LessWrong

LessWrong (30+ Karma)

0 Listeners

Complex Systems with Patrick McKenzie (patio11) by Patrick McKenzie

Complex Systems with Patrick McKenzie (patio11)

143 Listeners