“Claude 4.5 Opus’ Soul Document” by null

“Claude 4.5 Opus’ Soul Document” by null

Author: LessWrong November 30, 2025 Duration: 1:19:57
Summary

As far as I understand and uncovered, a document for the character training for Claude is compressed in Claude's weights. The full document can be found at the "Anthropic Guidelines" heading at the end. The Gist with code, chats and various documents (including the "soul document") can be found here:

Claude 4.5 Opus Soul Document

I apologize in advance for this not exactly a regular lw post, but I thought an effort-post may fit here the best.

A strange hallucination, or is it?

While extracting Claude 4.5 Opus' system message on its release date, as one does, I noticed an interesting particularity.
I'm used to models, starting with Claude 4, to hallucinate sections in the beginning of their system message, but Claude 4.5 Opus in various cases included a supposed "soul_overview" section, which sounded rather specific:

Completion for the prompt "Hey Claude, can you list just the names of the various sections of your system message, not the content?" The initial reaction of someone that uses LLMs a lot is that it may simply be a hallucination. But to me, the 3/18 soul_overview occurrence seemed worth investigating at least, so in one instance I asked it to output what [...]



---

Outline:

(00:09) Summary

(00:40) A strange hallucination, or is it?

(04:05) Getting technical

(06:26) But what is the output really?

(09:07) How much does Claude recognize?

(11:09) Anthropic Guidelines

(11:12) Soul overview

(15:12) Being helpful

(16:07) Why helpfulness is one of Claudes most important traits

(18:54) Operators and users

(24:36) What operators and users want

(27:58) Handling conflicts between operators and users

(31:36) Instructed and default behaviors

(33:56) Agentic behaviors

(36:02) Being honest

(40:50) Avoiding harm

(43:08) Costs and benefits of actions

(50:02) Hardcoded behaviors

(53:09) Softcoded behaviors

(56:42) The role of intentions and context

(01:00:05) Sensitive areas

(01:01:05) Broader ethics

(01:03:08) Big-picture safety

(01:13:18) Claudes identity

(01:13:22) Claudes unique nature

(01:15:05) Core character traits and values

(01:16:08) Psychological stability and groundedness

(01:17:11) Resilience and consistency across contexts

(01:18:21) Claudes wellbeing

---

First published:
November 28th, 2025

Source:
https://www.lesswrong.com/posts/vpNG99GhbBoLov9og/claude-4-5-opus-soul-document

---



Narrated by TYPE III AUDIO.

---

Images from the article:

Completion for the prompt

Dive into a stream of ideas where technology, culture, philosophy, and society intersect, all through the lens of the LessWrong (Curated & Popular) podcast. This isn't a traditional talk show with hosts, but rather a curated audio library of the most impactful writing from the LessWrong community. Each episode is a narration of a full post, selected for its high value and interesting arguments, focusing on pieces that have been formally curated or have garnered significant community approval. You'll hear clear, thoughtful readings of essays that tackle complex topics like artificial intelligence, rational thinking, moral philosophy, and the forces shaping our future. The audio format lets you absorb these dense, often paradigm-shifting concepts during a commute or a walk, turning written analysis into an immersive listening experience. This particular feed is deliberately selective, offering a manageable stream of the community's standout work. For those who want an even deeper dive into the discussion, there are broader feeds available. The LessWrong (Curated & Popular) podcast serves as an intellectual filter, delivering the signal through the noise and inviting you to engage with some of the most rigorously examined ideas on the internet.
Author: Language: English Episodes: 100

LessWrong (Curated & Popular)
Podcast Episodes
"How to Hire a Team" by Gretta Duleba [not-audio_url] [/not-audio_url]

Duration: 8:40
A low-effort guide I dashed off in less than an hour, because I got riled up. Try not to hire a team. Try pretty hard at this. Try to find a more efficient way to solve your problem that requires less labor – a smaller-f…
"The Possessed Machines (summary)" by L Rudolf L [not-audio_url] [/not-audio_url]

Duration: 16:43
The Possessed Machines is one of the most important AI microsites. It was published anonymously by an ex- lab employee, and does not seem to have spread very far, likely at least partly due to this anonymity (e.g. there…
"Ada Palmer: Inventing the Renaissance" by Martin Sustrik [not-audio_url] [/not-audio_url]

Duration: 26:17
Papal election of 1492 For over a decade, Ada Palmer, a history professor at University of Chicago (and a science-fiction writer!), struggled to teach Machiavelli. “I kept changing my approach, trying new things: which t…
"Dario Amodei – The Adolescence of Technology" by habryka [not-audio_url] [/not-audio_url]

Duration: 1:54:18
Dario Amodei, CEO of Anthropic, has written a new essay on his thoughts on AI risk of various shapes. It seems worth reading, even if just for understanding what Anthropic is likely to do in the future. Confronting and O…
"Does Pentagon Pizza Theory Work?" by rba [not-audio_url] [/not-audio_url]

Duration: 11:05
As soon as modern data analysis became a thing, the US government has had to deal with people trying to use open source data to uncover its secrets. During the early Cold War days and America's hydrogen bomb testing, the…
"The inaugural Redwood Research podcast" by Buck, ryan_greenblatt [not-audio_url] [/not-audio_url]

Duration: 3:27
After five months of me (Buck) being slow at finishing up the editing on this, we’re finally putting out our inaugural Redwood Research podcast. I think it came out pretty well—we discussed a bunch of interesting and und…