Unfaithful Chain of Thought

What's actually happening when an LLM "thinks out loud"? Research on human decision-making suggests that much of the reasoning we believe drives our choices is actually post hoc rationalization — we decide first, explain later. Katie and Ben get curious about whether the same might be true for large language models: when you watch a model reason through a problem in real time, is that chain of thought the genuine process, or just a plausible-sounding story told after the fact? It's a deceptively deep question with real stakes for how much we should trust model explanations. Miles Turpin et al., "Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting" (NeurIPS 2023, NYU and Anthropic): Anthropic, "Reasoning Models Don't Always Say What They Think" (Alignment Faking research, 2025):

You can listen to Unfaithful Chain of Thought online on Radio and Podcast. Open the player on this page to stream the available audio.

Unfaithful Chain of Thought is an episode from Linear Digressions by Ben Jaffe and Katie Malone.

This episode is 00:24:32 long.

This episode was published on Apr 13, 2026.

Yes. Use the heart button on the episode page to add it to your favorite episodes list.

Yes. This page shows related episodes from Linear Digressions when more episodes are available from the podcast feed.