Sign up to save your podcasts
Or
Share “Evaluating honesty and lie detection techniques on a diverse suite of dishonest models” by Sam Marks, Johannes Treutlein, evhub, Fabien Roger
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Evaluating honesty and lie detection techniques on a diverse suite of dishonest models” by Sam Marks, Johannes Treutlein, evhub, Fabien Roger
TL;DR: We use a suite of testbed settings where models lie—i.e. generate statements they believe to be false—to evaluate honesty and lie detection techniques. The best techniques we studied involved fine-tuning on generic anti-deception data and using prompts that encourage honesty.
Read the full Anthropic Alignment Science blog post and the X thread.
Introduction:
Suppose we had a “truth serum for AIs”: a technique that reliably transforms a language model $M$ into an honest model $M_H$ that generates text which is truthful to the best of its own knowledge. How useful would this discovery be for AI safety?
We believe it would be a major boon. Most obviously, we could deploy $M_H$ in place of $M$. Or, if our “truth serum” caused side-effects that limited $M_H$'s commercial value (like capabilities degradation or refusal to engage in harmless fictional roleplay), $M_H$ could still be used by AI developers as a tool for ensuring $M$'s safety. For example, we could use $M_H$ to audit $M$ for alignment pre-deployment. More ambitiously (and speculatively), while training $M$, we could leverage $M_H$ for oversight by incorporating $M_H$'s honest assessment when assigning rewards. Generally, we could hope to use $M_H$ to detect [...]
---
First published:
November 25th, 2025
Source:
https://www.lesswrong.com/posts/9f7JmoaMfwymgsW9S/evaluating-honesty-and-lie-detection-techniques-on-a-diverse
---
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.
View all episodes
By LessWrongTL;DR: We use a suite of testbed settings where models lie—i.e. generate statements they believe to be false—to evaluate honesty and lie detection techniques. The best techniques we studied involved fine-tuning on generic anti-deception data and using prompts that encourage honesty.
Read the full Anthropic Alignment Science blog post and the X thread.
Introduction:
Suppose we had a “truth serum for AIs”: a technique that reliably transforms a language model $M$ into an honest model $M_H$ that generates text which is truthful to the best of its own knowledge. How useful would this discovery be for AI safety?
We believe it would be a major boon. Most obviously, we could deploy $M_H$ in place of $M$. Or, if our “truth serum” caused side-effects that limited $M_H$'s commercial value (like capabilities degradation or refusal to engage in harmless fictional roleplay), $M_H$ could still be used by AI developers as a tool for ensuring $M$'s safety. For example, we could use $M_H$ to audit $M$ for alignment pre-deployment. More ambitiously (and speculatively), while training $M$, we could leverage $M_H$ for oversight by incorporating $M_H$'s honest assessment when assigning rewards. Generally, we could hope to use $M_H$ to detect [...]
---
First published:
November 25th, 2025
Source:
https://www.lesswrong.com/posts/9f7JmoaMfwymgsW9S/evaluating-honesty-and-lie-detection-techniques-on-a-diverse
---
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 shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,346 Listeners
Conversations with Tyler
2,451 Listeners
The Peter Attia Drive
8,603 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,186 Listeners
ManifoldOne
93 Listeners
Your Undivided Attention
1,598 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,935 Listeners
Machine Learning Street Talk (MLST)
95 Listeners
Dwarkesh Podcast
502 Listeners
Hard Fork
5,520 Listeners
The Ezra Klein Show
15,948 Listeners
Moonshots with Peter Diamandis
545 Listeners
No Priors: Artificial Intelligence | Technology | Startups
133 Listeners
Latent Space: The AI Engineer Podcast
93 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
467 Listeners