AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Raphaël Millière: The Vector Grounding Problem and Self-Consciousness
The Gradient: Perspectives on AI
The Emergence of Mechanistic Interpretability
The guiding thread is for me and what excites me moving forward is how can we have again building inspiration taking inspiration from working comparative and developmental psychology. I'm very excited in particular by this kind of emerging field of research called mechanistic interpretability that involves going beyond behavioral behavior or investing or before behavioral evaluation of the models using benchmarks. It actually tries to pry open these models and reverse engineer the circuits that emerge from training within these models but you cannot a priori know just by looking at the architecture of the model or its learning objective.
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