<p>What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/</p>

What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/

Takes on "Alignment Faking in Large Language Models"

Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.

Share Takes on "Alignment Faking in Large Language Models"

Sign up to save your podcasts

Takes on "Alignment Faking in Large Language Models"

Takes on "Alignment Faking in Large Language Models"

More shows like Joe Carlsmith Audio

The Joe Rogan Experience

Conversations with Tyler

Dwarkesh Podcast

Clearer Thinking with Spencer Greenberg