5min snip

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

E48: Mechanizing Mechanistic Interpretability with Arthur Conmy

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

NOTE

The Challenge of Predicting Unknown Capabilities and Evaluations in AI

The unknown capabilities of AI systems are difficult to predict and evaluate./nAI safety researchers are concerned about convergent instrumental goals in models./nKnown unknowns of concepts can emerge through training./nInterpretability techniques can help detect concerning behaviors in AI models./nMechanistic interpretability has a specific approach to understanding dangerous capabilities.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode