The Limits of Today's AI Models - Transformers, State Space Models, and the Future of Multimodal Intelligence

The Limits of Today's AI Models - Transformers, State Space Models, and the Future of Multimodal Intelligence

Y Combinator: The Vault via YouTube Direct link

— Introducing Cartesia

1 of 18

1 of 18

— Introducing Cartesia

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Limits of Today's AI Models - Transformers, State Space Models, and the Future of Multimodal Intelligence

Automatically move to the next video in the Classroom when playback concludes

  1. 1 — Introducing Cartesia
  2. 2 — From Architecture Research to Startup
  3. 3 — What “Architecture Research” Really Means
  4. 4 — Why Transformers Hit a Ceiling
  5. 5 — State Space Models Explained
  6. 6 — Intelligence as Compression
  7. 7 — Retrieval vs. Abstraction
  8. 8 — Hybrid Architectures and the Future
  9. 9 — Why Cartesia Chose Voice AI
  10. 10 — What Multimodality Actually Means
  11. 11 — Audio as a Recipe for Other Modalities
  12. 12 — Tokens, Representations, and Learning Signals
  13. 13 — Learning Representations End-to-End
  14. 14 — Building for the “Average Human”
  15. 15 — Research vs. Product Reality
  16. 16 — One Vision, Ruthlessly Executed
  17. 17 — Product as a Truth Serum for Research
  18. 18 — Startup Gravity Applies to Research Too

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.