Přejít k obsahu
Global sound
Linear Digressions

Linear Digressions

Unfaithful Chain of Thought

· 25 min

Poznámky k epizodě

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): https://arxiv.org/abs/2305.04388

Anthropic, "Reasoning Models Don't Always Say What They Think" (Alignment Faking research, 2025):
https://www.anthropic.com/research/reasoning-models-dont-say-think

Web: soundcloud.com

Živě, poslední hodina: 7 297 skladeb na 2 820 stanicích v 120 zemích

Objevte svět prostřednictvím rádia

Další způsoby objevování (7)

Slyšeli jste něco pěkného? Uložte si to, nebo to otevřete rovnou ve Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Ibiza PlayAbout RadioPokračovat v poslechu