Vibe Coding x Storytelling and AI/XR, intersections of GenAI

Welcome to a special edition of GenTalks, streamed live from The Lighthouse in Venice, CA. This session experiments with Discord, a new multi-camera setup, and a format that blends community check-ins with high-level guest discussions on the future of creative AI.We’re joined by two innovators approaching generative media from radically different directions:1. Parth Patil — Agentic Workflows & Vibe CodingParth walks through his journey from Clubhouse to building coding agents full-time. He discusses:Using Claude Code to build fully automated creative pipelinesLocal agent workflows that can handle editing, clipping, captioning, and video assemblyWhy coding agents matter more for non-technical creatorsThe origin story behind the “Reid Hoffman talks to Reid Hoffman” avatar experimentHis long-term focus on agent-driven games, world models, and emergent storytelling2. Jiajian Min — AI/XR Performance, Motion Capture & World ModelsJiajian presents extraordinary work combining dance, calligraphy, projection mapping, and generative models. Highlights include:Motion-capture-driven AI calligraphy created in collaboration with dancersHand-tracked real-time AI animation using Leap Motion + custom diffusion modelsAward-winning interactive installations presented at ACM MultimediaHarvard research digitizing Buddhist caves into immersive spatial environmentsPanoramic world-model theatre created for MIT: nested dreams, 360° projection, and live camera compositingThis session explores how creative AI is splitting into two powerful directions:(1) Agentic automation for scalable personal workflows(2) Embodied, immersive, spatial art beyond the 2D frameKey Topics CoveredVerticalization of creative toolchains (Figma, Weavy, Adobe, etc.)Agent-based coding and why local agents matterThe difference between Claude Code vs LM Studio vs typical web appsMotion capture + diffusion models in live performanceWorld models and panoramic generative imageryFuture of AI-native theatre and spatial storytellingHow AI augments the human body in ritual and performanceWhy games and interactive worlds may be the next frontier for creatorsTools MentionedClaude Code (Anthropic)Leap Motion / UltraleapTouchDesignerOptiTrackKinectWorldLabEarly avatar systems (Hour One-style pipelines)Opus Clips (as reference)DescriptWeavy00:00 — Discord setup chaos03:20 — Community check-in09:10 — Introduction of guest: Parth Patil12:00 — Parth’s GPT-4 origin story20:30 — Building “Reid Talks to Reid”28:00 — Why Claude Code is a creative game-changer35:00 — Automated podcast/pipeline example44:10 — Q&A on agents, apps, and iPhone development48:30 — Introduction of guest: Jiajian Min50:00 — Embodi Ink (dance + calligraphy)58:15 — Hand-tracked diffusion animation1:05:20 — Harvard Buddhist cave immersive1:10:40 — MIT panoramic theatre1:17:20 — Artistic philosophy of embodied AI1:21:00 — Final thoughts & upcoming sessions1:24:00 — Closing + next-day RoboDojo announcement