Skip to content
The Deep Dive: Subliminal Learning in AI — How Traits Travel Between Models episode artwork

Jul 24, 2025 7 min

The Deep Dive: Subliminal Learning in AI — How Traits Travel Between Models

from Intellectually Curious Hosted by Mike Breault

In this episode, we explore how advanced AI, especially large language models, can pick up non-semantic traits from data produced by other models. We cover the mechanism, the crucial role of shared initialization, why filtering fails to stop it, and the safety implications for AI development. Plus, practical takeaways for evaluating and safeguarding models beyond surface behavior. Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information. Sponsored by Embersilk LLC

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

The Deep Dive: Subliminal Learning in AI — How Traits Travel Between Models

0:00 7:06

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Intellectually Curious?

This episode is 7 minutes long.

When was this Intellectually Curious episode published?

This episode was published on July 24, 2025.

Can I download this Intellectually Curious episode?

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