AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Jesse Hoogland on Developmental Interpretability and Singular Learning Theory
The Inside View
The Universality Hypothesis for Learning Online
The hypothesis of universality says that many different models may be trained on many different kinds of data. The same structure that you have in Chris Ola's blog post on circuits for vision networks, every vision network would have the same circuit. So right now, this stuff is very empirical. And there's some more evidence, right? If you look at the way that humans process images, it's also similar to the way these models do it.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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