Brandon on Twitter / X

Thousands of Styled Rectangles in 120FPS on GPU

Secrets of rendering extremely fast UIs in WebGPU by minimizing overhead on the GPU.

vik on Twitter / X

Photon, our inference engine, isn't fast just because of GPU kernels. A lot of the speedup comes from engine-level work: request scheduling, prefix caching, image processing, all tuned to keep the GPU saturated. https://t.co/3M7eFcFKo5— vik (@vikhyatk) May 2, 2026

Spiral on Twitter / X

4/ Spiral is our database built on Vortex: • Direct S3 → GPU data loading (skip the CPU bottleneck) • One API for 10KB embeddings AND 4GB videos • Time-bounded, audited permissions (no more credentials passed to AI agents) • Actually saturates your GPUs— Spiral (@SpiralDB) September 11, 2025

Unsloth AI on Twitter / X

Inference in Unsloth Studio is now ~20% faster.You can also use older pre-downloaded GGUFs from Hugging Face etc.AMD chat support for Linux now works. Data Recipes now works on macOS, AMD, CPU setups.GitHub: https://t.co/aZWYAtakBPChangelog: https://t.co/npRrgSMYs3 pic.twitter.com/cnZvoG1TeN— Unsloth AI (@UnslothAI) March 27, 2026

Lee Robinson on Twitter / X

Watch a timelapse of GPT-5.2 building a browser!Both websites start out barely working, and then after millions of lines of code, the browser actually works.Pretty cool experiment with long-running agents. https://t.co/KT6HgHEivA pic.twitter.com/8EPbyih8cU— Lee Robinson (@leerob) January 14, 2026

Josh Miller on Twitter / X

Here's what @browsercompany's AI eng & ML teams are working on for @diabrowser right now:(This is a pitch to come work for us; info at end)🤖 COMPUTER USE – we've built our own bespoke APIs on top of Chromium to optimize latency, accuracy, and cost of computer-using agents.… pic.twitter.com/c989h1TYnQ— Josh Miller (@joshm) August 19, 2025

More performant, diverse Web engines – 26 March 2025

Slideset: https://docs.google.com/presentation/d/1f0fm5OpE7vwqQkKfNwvYuzH7O3WyPsK4xSIiegLplbg/edit#slide=id.p and archived PDF copy

Fast real-time website screenshot API | Thum.io

Thum.io provides real-time desktop and mobile screenshots of websites as a service. We are the only website screenshot generator to live stream thumbnails. Try it for free!

vincent on Twitter / X

Session management is working and now it will keep the model in memory instead of constantly loading. Now to fix the hardest part, gibberish issue.ALMOST THERE ~80% DONE 🔨🔨🔨Demo: @UnslothAI Llama 3.2 1B on CPU3.6 tokens/sec to about 4.1 tokens/sec (gibberish) pic.twitter.com/1tp8dXQrLo— vincent (@t0kenl1mit) August 5, 2025

Fast Embeddings on GPUs

Fast and accurate search is vital to all of Perplexity, from Search and Computer to our API Platform. Behind the scenes, the heavy lifting is done by embedding

0xSero on Twitter / X

I just had to make a new video of GLM-4.7-Flash - Helping me refactor VLLM studio - Did a data analytics report for work - Managed to search my tweets - Made me a fully playable Pacman in 1 shot- Great at browser useThis model is too good to be this small, the full thing… pic.twitter.com/EyRmsb7pWu— 0xSero (@0xSero) January 21, 2026

🚨 AI News | TestingCatalog on Twitter / X

OpenAI upgraded Computer Use for ChatGPT Work with picture-in-picture mode and faster execution. So users can see what it is doing 👀h/t @AriX pic.twitter.com/7WYIGGIuOo— 🚨 AI News | TestingCatalog (@testingcatalog) July 9, 2026

Silicon Jungle on Twitter / X

i’m glad they’re doing what they’re doing.but they have one thing wrong.this should be happening at the OS level, not the browser. https://t.co/GiSLenJ0bg— Silicon Jungle (@JungleSilicon) December 2, 2024

Ian Vanagas on Twitter / X

I've been enjoying writing screenshot essays lately because they provide more depth than tweets while being easier to finish and share than blogs.To help with this, I built a little app that makes it easier to make nice looking ones: https://t.co/mybEawgwgFEnjoy! https://t.co/gMHUCMzRbL— Ian Vanagas (@IanVanagas) March 30, 2024

Leveraging Rust and the GPU to render user interfaces at 120 FPS

From the Zed Blog: A deep-dive into the graphical underpinnings of GPUI, the hardware-accelerated framework that powers Zed's user interface.