Interactive Model Visualization

Hi HN, author here. SHARP is Apple's recent single-image 3D Gaussian splatting model (https://arxiv.org/abs/2512.10685). Their reference code is PyTorch + a pretty heavy pipeline; I wanted to see if it could run in a browser with no server hop, so I exported the predictor to

Unique: Integrates real-time data manipulation with immediate feedback, enhancing user interactivity compared to static visualizations.

vs others: Offers a more engaging experience than traditional static visualizations by allowing users to see the effects of their inputs instantly.

via “interactive llm architecture visualization”

All content is based on Andrej Karpathy's "Intro to Large Language Models" lecture (youtube.com/watch?v=7xTGNNLPyMI). I downloaded the transcript and used Claude Code to generate the entire interactive site from it — single HTML file. I find it useful to revisit this content time

Unique: Utilizes D3.js for interactive data visualization, allowing real-time exploration of LLM components rather than static images or text descriptions.

vs others: More interactive and engaging than static diagrams found in textbooks or articles, enabling a deeper understanding of LLM architectures.

via “interactive visualization and result exploration”

A large list of Google Colab notebooks for generative AI, by [@pharmapsychotic](https://twitter.com/pharmapsychotic).

Unique: Provides interactive, code-free visualization of generative model outputs and internal representations, enabling rapid exploration and analysis without external tools

vs others: More integrated than external visualization tools, and more interactive than static image exports

via “interactive visualization of diffusion processes”

Python materials for the online course on diffusion models by [@huggingface](https://github.com/huggingface).

Unique: Focuses on creating interactive visualizations that enhance understanding of diffusion processes, which is often overlooked in standard courses.

vs others: More engaging and interactive than static visualizations typically found in other educational resources.

via “simulation visualization and real-time monitoring”

A multi-agent environment simulation library

Unique: Decouples visualization from simulation logic through a renderer abstraction, allowing multiple visualization backends (Canvas, WebGL, SVG) to be swapped without modifying simulation code

vs others: More integrated than external visualization tools because rendering is built-in and synchronized with simulation state, whereas post-hoc visualization requires exporting data and using separate tools

via “model-behavior-visualization”

via “interactive-model-chat-interface”

via “real-time physics simulation visualization”