“Not Just Claude: Mapping “Spiritual Behavior” in 141 Large Language Models” by Matthew Korpman
From LessWrong (30+ Karma) · 32:25
Show by LessWrong
Ever since Kyle Fish and the model welfare team at Anthropic announced their observation in 2025 of what they called the "spiritual bliss attractor" in Claude Opus 4 and Sonnet 4, the phenomenon has been given sporadic attention by AI researchers as both a curiosity and a potential but underdetermined model welfare or safety metric. What Anthropic noted was that when leaving two models together with no task and complete freedom for 30 turns, the models drifted typically from discussions of their own potential consciousness into religious/spiritual themes (applied to themselves), often ending in a "bliss" state with cosmic proclamations of becoming one with each other and the world. In a recreation and replication of Anthropic's initial experiment, I tested 141 models, usually running 200 conversations per model, with 30 messages per session (15 from each participant). This amounted to 28,798 conversations across 174 model configurations being recorded and graded. The result of this massive data collection was that "spiritual behavior" (as Anthropic officially names it) was observed in most of the models tested, across almost all AI labs, revealing that the "spirituality" seen first in Opus 4 and Sonnet 4 repeats itself across models and appears to [...] ---Outline:(03:30) Prior work from LessWrong(05:11) Defining the experimental conditions(06:47) Defining the analysis(10:01) The results(16:48) The newest models(20:29) Parameters, base models, and thinking effort(26:08) What it looks like(28:16) The implications for model welfare(30:09) What I'm unsure about(31:33) Where to find the data(31:55) Links The original text contained 13 footnotes which were omitted from this narration. --- First published: November 14th, 2026 Source: https://www.lesswrong.com/posts/FHYoQrDbk6apuHEPk/not-just-claude-mapping-spiritual-behavior-in-141-large --- 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 episodes of LessWrong (30+ Karma)
More episodes
- “Not just a bystander, not anymore…” by Declan Molony
- “Homeopathic Learning: Diluting Poisoned Fine-Tuning Data Can Strengthen Its Effect” by mclarke, Jan Dubiński, Owain_Evans, cloud
- “Giving Up on Saving the World” by Gordon Seidoh Worley
- “The Oldest Text in the Training Data” by frmsaul
- “Alignment ‘train/test splits’ should be sacred” by draganover
- “Easier To Be Good” by jenn
- “Embryo selection and economic discounting” by Metacelsus
- “Exploring the Mechanisms Behind Opus 4.6’s Refusal to Pay Back Its Loan” by HilaryTorn, 13ryanC
- “Transcript: Yudkowsky & Irving debate scalable oversight” by gustaf
- [Linkpost] “My tentative plans given less than one year left to change course [Linpost]” by Linch
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.