This chapter delves into the scale of models used, concerns about upgrading core models for relevant investigations, training frontier models for interpretability work, different categories of facts associated with neural networks and transformers, and the evolution of interpretability in vision models. The discussion also touches on the challenges of transitioning from memorization to true reasoning in transformer models, the role of training data in enhancing models' reasoning abilities, and the desire for AI models to progress in reducing hallucinations and enhancing reasoning capabilities.

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