#webgpu

📝 New blog post: comics.skriv.ist: panel-by-panel comics in the browser, and the classifier that did nothing I set out to build guided-view comic reading on top of a new decision model. I ended up shipping a reader that runs entirely in your browser, and deleting the model it was designed around after measuring that it answered the same thing nineteen times in a row. https://blog.arda.tr/blog/2026-09-19-comics-skrivist #ai #dev #webgpu #onnx #comics #skrivist

Solving poker in custom WebGPU kernels https://phulin.me/blog/poker/ #HackerNews #Tech #WebGPU

Show HN: Manim (3Blue1Brown's animation engine) in the browser via WebGPU https://studio.academa.ai/ #HackerNews #Tech #WebGPU

WebGPU Unleashed: A Practical Tutorial https://shi-yan.github.io/webgpuunleashed/ #HackerNews #Tech #WebGPU

Learn WebGPU for C++ https://eliemichel.github.io/LearnWebGPU/ #HackerNews #Tech #WebGPU

Rendering Fonts Quickly on the GPU https://www.outercloud.dev/blogs/webgpu-font-rendering/ #HackerNews #Tech #WebGPU

Browser exploitation isn't web bugs. It's memory corruption across three processes. This issue walks the full chain: V8 JIT type confusion for arbitrary read/write, WebAssembly RWX pages to run shellcode, WebGPU/Dawn as the softer GPU-process target, and the renderer→GPU→broker sandbox escape that ends in --no-sandbox. https://www.kayssel.com/newsletter/issue-59/ #InfoSec #CyberSecurity #Pentesting #BugBounty #BinaryExploitation #WebGPU

Browser-Based Image Inpainting Runs Locally, If One Doesn’t Mind A Big Download https://hackaday.com/2026/07/10/browser-based-image-inpainting-runs-locally-if-one-doesnt-mind-a-big-download/ #ArtificialIntelligence #SoftwareHacks #Ai #Coding #Inpainting #Onxx #Webgpu

New week, new slides: Run LLMs Locally Added OpenAI's Privacy-Filter model using privacy-filter.cpp. New slides about economics and hardware used by the Hugging Face community. https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf #ai #llm #llamacpp #wllama #stablediffusion #qwen #localai #gemma4 #webgpu #opencode #huggingface #privacy #digitalsovereignty

New update for the slides of my talk "Run LLMs Locally": WebGPU Now models can run completely inside the browser using Transformer.js, Vulkan and WebGPU (slower than llama.cpp, but already usable). https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #webgpu