AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
13min chapter
Francois Chollet, Mike Knoop - LLMs won’t lead to AGI - $1,000,000 Prize to find true solution
Dwarkesh Podcast
Challenges in Developing Multimodal Models for Spatial Reasoning
The chapter delves into the difficulties faced in developing multimodal models for spatial reasoning, discussing the core knowledge required for tasks like Arc challenges such as object characteristics, counting, and geometry. It compares the struggles of current models with recognizing patterns in tasks like working with numbers and highlights the capabilities and limitations of Language Model Models (LLMs) in tasks like ARC. The conversation also touches on the importance of active inference and scaling maximalists in improving the performance of AI systems.
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