A coding agent generated images of Paris monuments using ideogram-ai/ideogram4, then reconstructed each as a 3D Gaussian splat (.ply file) using VAST-AI/TripoSplat, and deployed the result as a static interactive Space with a Three.js viewer.
Every Gradio Space now exposes a plain-text agents.md file that tells an agent the exact API schema, call templates, file-upload method, and auth requirements—eliminating the need for client libraries or hardcoded integrations. The agent compressed the output splats to .ksplat (~3× smaller) and auto-framed each monument.
The barrier to chaining multimedia models (image generation, 3D reconstruction) from different organizations is largely removed; an agent can now assemble documented, callable blocks from the Hub the same way it combines code libraries, with zero integration code required.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
NVIDIA released Nemotron 3.5 Super VL, an open-weight model with 120 billion parameters that handles text, ima…
NVIDIA released Nemotron 3.5 Bolt 74B-A9B 24GB, an AI model for local agents that hits over 80 tokens per seco…
Black Forest Labs released FLUX 3 Image Klein as open weights on October 15, 2026 — a 5.6B-parameter model for…
PrismML released Ternary Bonsai 2 2B, 4B and 9B on October 15, 2026, remade from Qwen3.5 to process in three v…
Apple released MLX today, which runs the 816B-parameter Muse Spark Open on four Mac Studios at over 36 tokens…
Meta launched Muse Spark Open, an open-weight model with 816 billion parameters and a 1 million token context…
