How OpenAI Trained SORA & What CTO is NOT Saying...
Join AI Productivity Hub & Setup Your AI Second Brain in 10min: https://dub.sh/join-aiph We will be able to generate new AI environments & modify our existing environments when capabilities of OpenAI Sora merge with what Apple calls Spatial Computing enabled now by Apple Vision Pro. While now, in 2024, these technologies exist in silos, eventually all technologies merge. Think how every phone now has touch screen, apps and powerful cameras. I hope that this video provides a moment of zooming out and provides a perspective into how every development happening at Big Tech companies come together in unison and how the world might look like in the future (near future at that). Curious to hear your thought what do you think? ⬇️Resources mentioned in this video⬇️ - Open AI Sora Technical Report "Video generation models as world simulators" https://openai.com/sora - Google Research on Photorealistic video: https://arxiv.org/abs/2312.06662 - Tim Brooks (Sora team) tweet: https://x.com/_tim_brooks/status/1758194111889490403?s=20 - Apple Vision Pro Matrix : https://x.com/vr_oasis/status/1764319395994579288?s=20 - Space Time Paches Reseach: https://arxiv.org/abs/2307.06304 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929 - Lucas Beyer : https://twitter.com/giffmana Thank you so much for watching and joining me on this journey! Let me know in the comments what you would like to see more of in the future. Bye!
