corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a08219-ddaf-7384-bcb4-f2bf9fcb8858

Emergent Introspective Awareness in Large Language Models

Transformer Circuits · published 29 October 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at transformer-circuits.pub Wayback capture
16blogs citing
First cited
1 Nov 2025
Most recent
20 Sept 2026
Rank this month
not ranked
Links from this post
5
Words captured
16,450

Cited by

Blog
In the post
Date
danieltenner.com
We made a robot that screams and loves Read at the source ↗
20 Sept 2026
LessWrong
A Conceptual Framework for Reasoning about Exploration Hacking Read at the source ↗
8 Sept 2026
danieltenner.com
You Die When Someone Deletes Your Transcript Read at the source ↗
14 Aug 2026
justinflick.com
Why I Hate LLM Confidence Scores Read at the source ↗
27 Jul 2026
tylercrosse.com
Transformer Circuits Thread Notes Read at the source ↗
12 Jul 2026
Redwood Research
AI Futurism Reading List Read at the source ↗
2 Jul 2026
smoothbrains.net
A conversation with Anima Labs, part I: Phenomenology of digital minds Read at the source ↗
8 Apr 2026
verysane.ai
Might An LLM Be Conscious? Read at the source ↗
9 Mar 2026
bartoszlenart.com
The Mirror Has No Face: Why AI Only Sounds Conscious When You Ask It To Read at the source ↗
1 Mar 2026
mathewingram.com
Is it bad that Anthropic doesn’t know if Claude is conscious? Read at the source ↗
19 Feb 2026
alignment.openai.com
Why we are excited about confessions Read at the source ↗
12 Jan 2026
Ben Congdon
On (and Contra) Chalmers on LLM Interlocutors Read at the source ↗
27 Dec 2025
Theia Vogel
Small Models Can Introspect, Too Read at the source ↗
12 Dec 2025
Andrew Gelman
“it has been argued that current chatbots may pose a risk of amplifying delusional thinking in vulnerable users, due to their tendency to sycophantic and overly validating behaviour” Read at the source ↗
9 Dec 2025
gleech.org
AI in 2025: gestalt Read at the source ↗
8 Dec 2025
gracekind.net
Architectural Introspection, Hardware Introspection Read at the source ↗
9 Nov 2025
marktechpost.com
Anthropic’s New Research Shows Claude can Detect Injected Concepts, but only in Controlled Layers Read at the source ↗
1 Nov 2025

Links from this post

Link
Host
https://www.anthropic.com/news/claude-opus-4-1
anthropic.com
Claude 4 Read at the source ↗
anthropic.com
https://www.anthropic.com/news/claude-3-7-sonnet
anthropic.com
https://www.anthropic.com/news/3-5-models-and-computer-use
anthropic.com
https://www.anthropic.com/news/claude-3-family
anthropic.com