{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/655148df2861630012a1d01b/68596b9abd94a78be6710b72?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Shivay Lamba: How to run secure AI anywhere with WebAssembly","thumbnail_width":200,"thumbnail_height":200,"thumbnail_url":"https://open-images.acast.com/shows/655148df2861630012a1d01b/1750690533034-c4393176-57e8-4fa7-97d4-efb2c5ce85cf.jpeg?height=200","description":"<p>Links</p><p>- CodeCrafters (partner): https://tej.as/codecrafters</p><p>- WebAssembly on Kubernetes: https://www.cncf.io/blog/2024/03/12/webassembly-on-kubernetes-from-containers-to-wasm-part-01/</p><p>- Shivay on X: https://x.com/howdevelop</p><p>- Tejas on X: https://x.com/tejaskumar_</p><p><br></p><p>Summary</p><p><br></p><p>In this podcast episode, Shivay Lamba and I discuss the integration of WebAssembly with AI and machine learning, exploring its implications for developers. We dive into the benefits of running machine learning models in the browser, the significance of edge computing, and the performance advantages of WebAssembly over traditional serverless architectures. The conversation also touches on emerging hardware solutions for AI inference and the importance of accessibility in software development. Shivay shares insights on how developers can leverage these technologies to build efficient and privacy-focused applications.</p><p><br></p><p>Chapters</p><p><br></p><p>00:00 Shivay Lamba</p><p>03:02 Introduction and Background</p><p>06:02 WebAssembly and AI Integration</p><p>08:47 Machine Learning on the Edge</p><p>11:43 Privacy and Data Security in AI</p><p>15:00 Quantization and Model Optimization</p><p>17:52 Tools for Running AI Models in the Browser</p><p>32:13 Understanding TensorFlow.js and Its Architecture</p><p>37:58 Custom Operations and Model Compatibility</p><p>41:56 Overcoming Limitations in JavaScript ML Workloads</p><p>46:00 Demos and Practical Applications of TensorFlow.js</p><p>54:22 Server-Side AI Inference with WebAssembly</p><p>01:02:42 Building AI Inference APIs with WebAssembly</p><p>01:04:39 WebAssembly and Machine Learning Inference</p><p>01:10:56 Summarizing the Benefits of WebAssembly for Developers</p><p>01:15:43 Learning Curve for Developers in Machine Learning</p><p>01:21:10 Hardware Considerations for WebAssembly and AI</p><p>01:27:35 Comparing Inference Speeds of AI Models</p><p><br></p>","author_name":"Tejas Kumar"}