A New Approach To AI Models

ℹ️ EPISODE INFO

Released

January 9, 2026

Duration

18m

Channel

YC Root Access

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

During last month’s NeurIPS 2025 conference, YC’s Ankit Gupta sat down with Karan Goel, founder and CEO of Cartesia, to explain why today’s AI architectures may be fundamentally limited. They discuss why transformers behave more like retrieval systems than learning systems, how state space models enable compression and abstraction, and why multimodal intelligence may require a whole new approach. The conversation also covers why Cartesia chose AI voice as a wedge product, and how research-driven companies can balance deep technical bets with real-world product discipline. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs Chapters: 00:11 — Introducing Cartesia 00:26 — From Architecture Research to Startup 01:20 — What “Architecture Research” Really Means 02:18 — Why Transformers Hit a Ceiling 03:33 — State Space Models Explained 04:21 — Intelligence as Compression 05:47 — Retrieval vs. Abstraction 06:41 — Hybrid Architectures and the Future 07:13 — Why Cartesia Chose Voice AI 08:25 — What Multimodality Actually Means 09:20 — Audio as a Recipe for Other Modalities 10:09 — Tokens, Representations, and Learning Signals 11:37 — Learning Representations End-to-End 12:29 — Building for the “Average Human” 13:54 — Research vs. Product Reality 15:18 — One Vision, Ruthlessly Executed 16:28 — Product as a Truth Serum for Research 17:25 — Startup Gravity Applies to Research Too

🎤 SPEAKERS

• Ankit Gupta

  host

  YC host/interviewer.

• Karan Goel

  guest

  CEO of Cartesia and former Stanford (Chris Ré lab) researcher.

🧾 EPISODE SUMMARY

In this episode of YC Root Access, featuring Ankit Gupta and Karan Goel, A New Approach To AI Models explores Cartesia’s bet: beyond transformers via compression-driven multimodal architectures for voice Cartesia was founded by Stanford PhD researchers to commercialize “architecture research,” not just scale existing transformer recipes.

🔗 RELATED EPISODES

The Future of AI Molecular Discovery

This Startup Is Trying To Solve The AI Memory Problem

Lessons from Building Open Source Libraries

The End of the Designer–Engineer Divide

Veriff: The Global Identity Infrastructure

Parahelp: The End-to-End AI Support Agent