Skip to content
No PriorsNo Priors

How AI Will Transform Roblox Games into Photorealistic Worlds | CEO David Baszucki

From “virtual doppelgängers” to “real-time dreaming,” online gaming platform Roblox is using AI technology to build the “Holodeck” envisioned in science fiction decades ago. Sarah Guo and Elad Gil sit down with Roblox CEO Dave Baszucki at Roblox headquarters to explore the intersection of AI, physics simulation, and the future of human connection. Dave discusses the evolution of the 4D creation tool in Roblox, a high-fidelity simulation that enables thousands of people to interact in real-time with photo-realistic graphics and acoustic physics. Dave reveals how Roblox is leveraging 13 billion hours of monthly user data to train native AI models that go beyond simple LLMs, enabling NPCs that can navigate and play games with human-like intuition. He also talks about how immersive communication will change video conferencing, how Roblox searches for unlikely talent outside of traditional elite universities, and how he balances rapid weekly iterations with keeping a “long view” on Roblox’s vision. Sign up for new podcasts every week. Email feedback to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @DavidBaszucki | @Roblox Chapters: 00:00 – Cold Open 00:36 – Dave Baszucki Introduction 01:16 – Realizing Robolox’s 20-Year Vision 05:29 – Using 4D Immersive Simulations in Virtual Interactions 08:22 – Physics Engine vs. Photorealism 11:50 – Storing Roblox History as Vector Data 14:00 – Training NPCs - Moving Beyond LLMs 18:05 – The Future of the Game Designer 19:54 – Video Latent World Models 23:53 – Social Simulation - AI Companions and Virtual Relationships 27:26 – Why Asset Costs Haven’t Changed the Gaming Industry 29:52 – AI Coding in Roblox Studio 31:36 – The Roblox Creator Economy 33:57 – Long-Term Conviction vs. Weekly Iteration 37:50 – Dave’s Hiring Philosophy for Roblox 43:44 – Conclusion

Elad GilhostDave BaszuckiguestSarah Guohost
Feb 4, 202643mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Roblox’s AI roadmap: Holodeck realism, NPCs, and creator leverage

  1. Baszucki frames Roblox as a 20-year mission to build a high-fidelity, physics-backed “human co-experience” platform—often likened to the Holodeck/metaverse—where AI primarily serves to accelerate realism, scale, and creation.
  2. He contrasts that multiplayer future with an opposite extreme: “real-time dreaming,” where AI generates personalized worlds populated mostly by NPCs, and suggests many hybrid products will emerge between these poles.
  3. A major technical emphasis is synchronization and memory for 10,000-player simulations, plus storing Roblox’s history as replayable vector data (not raster video) for safety, user replay, and training next-gen NPCs.
  4. He anticipates NPCs evolving beyond LLM chat into embodied agents trained on Roblox interaction data, potentially enabling opt-in personal “virtual doppelgängers,” while creators gain leverage via AI-assisted building, testing, and live-ops iteration.

IDEAS WORTH REMEMBERING

5 ideas

Roblox’s north star is stable: physics-backed co-experience at massive scale.

Baszucki describes a long-standing spec—10,000 people, real-time modification, photorealism, NPCs—arguing AI is mainly an accelerator toward that destination rather than a reason to change direction.

“4D” is about function and interaction, not just 3D visuals.

He uses 4D to mean simulation with behavior (physics, acoustics, persistence) that enables actions like walking around an office, natural proximity audio, or manipulating objects—capabilities video calls can’t match.

The hard problem is multiplayer synchronization and shared memory, not just graphics.

Baszucki highlights the challenge of efficiently synchronizing the state/history of 10,000 participants—where they were, what they did—suggesting future systems may blend native 3D representations with video/latent approaches.

Roblox wants to store “everything that happened” as vector history.

He proposes recording Roblox events as vector data to enable playback from any camera angle, support safety investigations, and let users remix meaningful moments—while emphasizing privacy-compliant, judicious use.

Next-gen NPCs will be trained from embodied gameplay data, not only text.

Roblox is training NPCs that can navigate and play games using platform interaction data; the roadmap escalates from generally competent NPCs to opt-in personalized models capturing gestures/behavior, and eventually agentic “virtual doppelgängers.”},{

WORDS WORTH SAVING

5 quotes

We do have that business plan slide… it imagined… the Holodeck… the ultimate high-fidelity simulation where people can come together and do stuff.

— Dave Baszucki

As the technology for multiplayer 4D simulation gets better and more photorealistic, it’s almost gonna be like video is the downsampling.

— Dave Baszucki

Part of the vision for us is to ultimately store the history of everything on Roblox… not raster like video, but… vector… the ability to play back anything that’s ever happened on Roblox.

— Dave Baszucki

The data we have, which is 13 billion hours a month, is… very powerful data… around how to create great NPCs that are more than just an LLM.

— Dave Baszucki

No matter how cheap it is to create assets, the expectation of quality from consumers goes up at exactly the same velocity.

— Dave Baszucki

20-year “Holodeck” vision and human co-experience4D simulation for communication beyond ZoomPhysics simulation vs. photorealism priorities10,000-player state synchronization and memoryVector-based historical replay of Roblox eventsNPC training beyond LLMs; embodied agents and doppelgängersCreator tooling: AI coding, environment generation, cloud live-ops

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome