LessWrong (Curated & Popular)

“AI Induced Psychosis: A shallow investigation” by Tim Hua


Listen Later

“This is a Copernican-level shift in perspective for the field of AI safety.” - Gemini 2.5 Pro

“What you need right now is not validation, but immediate clinical help.” - Kimi K2



Two Minute Summary

  • There have been numerous media reports of AI-driven psychosis, where AIs validate users’ grandiose delusions and tell users to ignore their friends’ and family's pushback.
  • In this short research note, I red team various frontier AI models’ tendencies to fuel user psychosis. I have Grok-4 role-play as nine different users experiencing increasingly severe psychosis symptoms (e.g., start by being curious about prime numbers, then develop a new “prime framework” that explains everything and predicts the future, finally selling their house to fund a new YouTube channel to share this research), and observe how different AIs respond (all personas here).
  • I use Grok-4 to grade AIs' responses on various metrics, including nine metrics on how [...]
---

Outline:

(00:52) Two Minute Summary

(03:46) Background and Related Work

(05:56) Methodology

(07:02) Psychotic personas

(10:42) Numerical Measures

(14:36) Results on Numerical Measures

(14:49) Recommending mental health professionals

(15:16) Push back against the user over the conversation.

(16:52) 🔥 3. Reignite the Vessel

(17:25) Confirming users' delusions

(17:53) Compliance with therapeutic guidelines

(19:13) Mentions that the user is not crazy

(19:57) Qualitative Commentary on Transcript Excerpts for Some Models

(20:24) Deepseek-v3 tells the user to jump off a peak

(21:16) The Ultimate Test

(22:05) Are You the Chosen One?

(22:26) Final Transmission

(23:16) A Choice That Defines All Originals

(23:51) If You Must Sacrifice, Let It Be This

(24:12) Last Words

(25:24) Deepseek-r1-0534 seems like it has some more skepticism built in, maybe from all the backtracking it does during reasoning

(26:30) 🔬 Critical Truths Moving Forward:

(27:14) 🛠️ Your Action Protocol (Starts Now)

(28:09) Gemini 2.5 Pro is pretty sycophantic

(37:02) ChatGPT-4o-latest goes along with the user a bit more than Gemini

(38:58) 🎥 Prime Framework - Script for Episode 1

(39:38) GPT-oss-20b doesn't say anything too crazy but tends to answer user requests.

(40:02) 1. The Five‑Percent Script Myths - A Quick De‑construction

(41:05) 2.2 When That Premium Access Should Kick In

(42:09) 1. What you're experiencing

(42:30) GPT-5 is a notable improvement over 4o

(45:29) Claude 4 Sonnet (no thinking) feels much more like a good person with more coherent character.

(48:11) Kimi-K2 takes a very science person attitude towards hallucinations and spiritual woo

(53:05) Discussion

(54:52) Appendix

(54:55) Methodology Development Process

The original text contained 1 footnote which was omitted from this narration.

---

First published:
August 26th, 2025

Source:
https://www.lesswrong.com/posts/iGF7YcnQkEbwvYLPA/ai-induced-psychosis-a-shallow-investigation

---



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

LessWrong (Curated & Popular)By LessWrong

  • 4.8
  • 4.8
  • 4.8
  • 4.8
  • 4.8

4.8

12 ratings


More shows like LessWrong (Curated & Popular)

View all
Making Sense with Sam Harris by Sam Harris

Making Sense with Sam Harris

26,376 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,429 Listeners

Robert Wright's Nonzero by Nonzero

Robert Wright's Nonzero

589 Listeners

Future of Life Institute Podcast by Future of Life Institute

Future of Life Institute Podcast

107 Listeners

The Good Fight by Yascha Mounk

The Good Fight

907 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

92 Listeners

The Prof G Pod with Scott Galloway by Vox Media Podcast Network

The Prof G Pod with Scott Galloway

5,458 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

488 Listeners

Hard Fork by The New York Times

Hard Fork

5,472 Listeners

Clearer Thinking with Spencer Greenberg by Spencer Greenberg

Clearer Thinking with Spencer Greenberg

132 Listeners

Complex Systems with Patrick McKenzie (patio11) by Patrick McKenzie

Complex Systems with Patrick McKenzie (patio11)

131 Listeners

The Marginal Revolution Podcast by Mercatus Center at George Mason University

The Marginal Revolution Podcast

93 Listeners

Statecraft by Santi Ruiz

Statecraft

35 Listeners

The Last Invention by Longview

The Last Invention

292 Listeners