This weekend in Generative Media

AI Photoshopping; AI NPCs in games; Where Congress might regulate AI

• A.I. Photoshopping Is About to Get Very Easy. Maybe Too Easy. (New York Times)

• NVIDIA's generative AI lets gamers converse with NPCs (Engadget)

• Opinion: Congress wants to regulate AI. Here’s where to start. (Washington Post)

• An A.I.-Generated Film Depicts Human Loneliness, in “Thank You for Not Answering” (New Yorker)

• Workers Are Terrified About AI. What Can They Do About It? (Daily Beast)

• OpenAI says it could ‘cease operating’ in the EU if it can’t comply with future regulation (The Verge)

• Will A Storm Of AI-Generated Misinfo Flood The 2024 Election? A Few Dems Seek To Get Ahead Of It (Talking Points Memo)

• Here’s What Happens When Your Lawyer Uses ChatGPT (New York Times)

• AI writing assistants can cause biased thinking in their users (Ars Technica)

• Conversational holograms that you can actually talk to — powered by Looking Glass and ChatGPT. No typing required. (Looking Glass)

• How to clone in the NeRF space 🤯🤯🤯 (Twitter) - workflow using 32 GoPros, lots of Photoshop, and Luma AI.

• Nvidia GeForce Driver Promises Doubled Stable Diffusion Performance (Tom’s Hardware)

• A Neural Space-Time Representation for Text-to-Image Personalization (arXiv)

• Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models (arXiv). Code available (GitHub)

• Deceptive-NeRF: Enhancing NeRF Reconstruction using Pseudo-Observations from Diffusion Models (arXiv)

• ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis (arXiv)

• Break-A-Scene: Extracting Multiple Concepts from a Single Image (Project page)