Bulletin · UTC
Merged timeline: 5 items (blog publish time and listing createdAt in UTC). For registry-only weekly slices, use /new.
VOID removes objects from videos along with all interactions they induce on the scene. It handles not just secondary effects like shadows and reflections, but also physical interactions like objects falling when a perso…
- LLMSeedance 2.0
Seedance 2.0 is a multi-modal audio-video generation model that supports text, image, audio, and video inputs with improved generation quality and speed. It delivers substantial improvements across all key sub-dimension…
Describe what you want; Claude drafts the first version. Refine in-thread, pull in your design system from code and files, then export or ship to Claude Code. Here is what Anthropic is claiming—and where to try it.
Z.AI’s GLM-5.1 is a long-horizon flagship model for agentic engineering. Here’s how to run it from the Hugging Face hub, Ollama, or the official API—with clear commands and realistic hardware expectations.
VOID is Netflix’s open video inpainting stack for deleting objects and the motion they cause. Recap of the Hugging Face model card, the explainx LLM directory page, and where consumer tools like BgBlur fit (similar problem, not the same model).