Skip to content
Emergent Introspective Awareness in Large Language Models episode artwork

Nov 3, 2025 15 min

Emergent Introspective Awareness in Large Language Models

from Best AI papers explained Hosted by Enoch H. Kang

This research by anthropic investigates the existence of **functional introspective awareness** in large language models (LLMs), specifically focusing on Anthropic's Claude models. The core methodology involves using **concept injection**, where researchers manipulate a model's internal activations with representations of specific concepts to see if the model can accurately **report on these altered internal states**. Experiments demonstrate that models can, at times, notice injected "thoughts," distinguish these internal representations from text inputs, detect when pre-filled outputs were unintentional by referring to prior intentions, and even **modulate their internal states** when instructed to "think about" a concept. The findings indicate that while this introspective capacity is often **unreliable and context-dependent**, the most capable models, such as Claude Opus 4 and 4.1, exhibit the strongest signs of this ability, suggesting it may emerge with increased model sophistication.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Emergent Introspective Awareness in Large Language Models

0:00 15:41

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Best AI papers explained?

This episode is 15 minutes long.

When was this Best AI papers explained episode published?

This episode was published on November 3, 2025.

Can I download this Best AI papers explained episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.