Today in Generative Media

Google's Gemini can hear; Spotify launches AI playlists; Artists' AI dilemma

• Google’s Gemini 1.5 Pro can now hear (The Verge)

• Spotify launches personalized AI playlists that you can build using prompts (TechCrunch)

• Artists’ AI dilemma: can artificial intelligence make intelligent art? (The Guardian)

• OpenAI prepares to fight for its life as legal troubles mount (Washington Post)

• AI Set to Become ‘Single Biggest Driver of Change’ in the Industry, Says AlixPartners’ Mark Endemaño, but Keep an Eye Also for ‘Spandex and Spray Tans’ (Variety)

• MIT License text becomes viral “sad girl” piano ballad generated by AI (Ars Technica)

• AI-generated entry wins Pink Floyd’s Dark Side of the Moon video competition (Entertainment Weekly)

• Card game developer says it paid an 'AI artist' $90,000 to generate card art because 'no one comes close to the quality he delivers' (PC Gamer)

• ‘Inceptionism’ and Balenciaga popes: a brief history of deepfakes (The Guardian)

• Deloitte Digital Using Adobe To Bring Personalization-At-Scale To Life (Forbes)

• Attention in transformers, visually explained (YouTube)

• StructLDM: Structured Latent Diffusion for 3D Human Generation (project page)

• BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling (project page)

• 🚀 So glad to announce that the foundation model behind 3D GenAI Rodin Gen-1, CLAY has been officially accepted by SIGGRAPH Technical Paper Journal Track. (X)

• I just open-sourced my Colab Notebook which lets you generate Magic: The Gathering cards just by providing an image (X)

• 17fps 1280x1024 continuous RT video gen. on 4090 (X)

• White collar work is secretly based on an apprenticeship system that will break (X)