The Engineering Behind the World’s Most Advanced Video AI

The Engineering Behind the World’s Most Advanced Video AI

From Gradient Dissent: Conversations on AI by Lukas Biewald

December 1, 2025 · 15 min · Season 1 · Episode 132

About this episode

Lukas Biewald interviews Cristóbal Valenzuela about the advancements in video AI and its implications for AGI.

Is video AI a viable path toward AGI?  Runway ML founder Cristóbal Valenzuela joins Lukas Biewald just after Gen 4.5 reached the #1 position on the Video Arena Leaderboard, according to community voting on Artificial Analysis .  Lukas examines how a focused research team at Runway outpaced much larger organizations like Google and Meta in one of the most compute-intensive areas of machine learning. Cristóbal breaks down the architecture behind Gen 4.5 and explains the role of “taste” in model development. He details the engineering improvements in motion and camera control that solve long-standing issues like the restrictive “tripod look,” and shares why video models are starting to function as simulation engines with applications beyond media generation. Connect with us here: Cristóbal Valenzuela: https://www.linkedin.com/in/cvalenzuelab Runway: https://www.linkedin.com/company/runwayml/ Lukas Biewald: https://www.linkedin.com/in/lbiewald/ Weights & Biases: https://www.linkedin.com/company/wandb/

People in this episode

Host: Lukas Biewald

Guest: Cristóbal Valenzuela

Topics covered

  • video AI
  • AGI
  • machine learning
  • model development
  • engineering improvements

Keywords

  • video AI
  • AGI
  • Runway ML
  • machine learning
  • model architecture
  • simulation engines
  • motion control

Mentioned in this episode

Organizations: Runway ML, Google, Meta, Artificial Analysis

More episodes of Gradient Dissent: Conversations on AI

Explore listener stats, chart rankings, contacts and more on the Gradient Dissent: Conversations on AI podcast page.