When Anthropic Asked Claude What it Was Thinking

Name: When Anthropic Asked Claude What it Was Thinking
Uploaded: 2026-10-23T13:49:07+00:00
Channel: Lenny's Podcast
Description: You can ask an AI what it was just thinking. Then you can check its answer against what's actually going on inside. Emmanuel Ameisen, Interpretability Researcher at Anthropic, on the Spanish-to-French experiment that suggests models have two kinds of processing: a higher-order one and a lower-order one.

Lenny's PodcastPodcast · il y a 3 heures

Voir sur YouTube

You can ask an AI what it was just thinking. Then you can check its answer against what's actually going on inside. Emmanuel Ameisen, Interpretability Researcher at Anthropic, on the Spanish-to-French experiment that suggests models have two kinds of processing: a higher-order one and a lower-order one.

Discussion

Rejoignez la communauté pour réagir et poser vos questions.

Aucun message pour l'instant. Lancez la discussion !