Ex-OpenAI duo launch ACTx486, turning any video into an interactive medium you can talk to
jakubzegzulka · x · 2026-09-24
Former OpenAI colleagues Karina Nguyen and Jakub Zegzulka launched ACTx486, a research demo for a new interactive medium. Their thesis: AI products shouldn't start with an empty chat box, which pushes the burden of deciding where to begin onto users. Instead, ACTx486 starts with an existing video (their example is a podcast) that already has narrative, pacing, and context.
- Viewers can tap the video to ask questions, interrupt, follow threads, generate real-time diagrams synced to the host's speech, switch languages, or send key points to their phone as cards and return to the video
- Answers are personalized via a viewer profile; the host asks clarifying questions when prompts are vague
- Follow-ups can add new dialogue inside generated "new worlds" while the original audio keeps playing untouched
The user becomes a "microdirector," shaping the experience without having to decide where it goes — and they argue any video could become something you can talk to.
More from Multimodal
- Endless screensaver of self-assembling quantum cryostats, made with Gemini 4 Carbon — hapticdata · 2026-11-12
- Apple's ADM 3 Cloud image model ranks #42 in editing and #85 in text-to-image on Artificial Analysis arena — ArtificialAnlys · 2026-11-12
- Adobe Firefly debuts Story Builder tool for streamlined visual storytelling — LudovicCreator · 2026-11-12
- Intangible 2.0 Launches as One AI Studio Unifying Image, Video and 3D Models — umesh_ai · 2026-11-12
- From one product image to a spy-movie ad: agent-driven video creation — hey_abusiddik · 2026-11-12
- Claude writes a Bach-style organ fugue in LilyPond with a single prompt — IgorCarron · 2026-11-12