2min chapter

LessWrong (Curated & Popular) cover image

[HUMAN VOICE] "How useful is mechanistic interpretability?" by ryan_greenblatt, Neel Nanda, Buck, habryka

LessWrong (Curated & Popular)

CHAPTER

Exploring Model Safety and Ablations

This chapter discusses the speakers' doubts about the effectiveness of enumerative safety and the challenges posed by superhuman models. It also explores the concept of ablations and proposes retraining the model and augmenting smaller models with explanations for better performance.

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