I've never sen anything more accurate

I’m mad I didn’t think of this first 😭 this is so fun and creative

Japan knows how to OREO

Will it run DOOM?

I know you're all getting mighty tired of seeing typography on your timeline today! But here's a pretext.js demo that (hopefully) isn't a crime against justification and indentation.

John is killing it! He has being pushing my TurboQuant MLX implementation to the max. In the video below he uses to process 265K context using Qwen3.5-4B 🚀 It achieves 500ms TTFT and a reasonable 40 tok/s.

mlx-vlm v0.4.3 is here 🚀 Day-0 support: 🔥 Gemma 4 (vision, audio, MoE) by Google DeepMind 🦅 Falcon-OCR + Falcon Perception by Technology Innovation Institute 🪨 Granite Vision 4.0 by IBM Research New models: 🎯 SAM 3.1 with Object Multiplex by Facebook 🔍 RF-DETR detection & segmentation by

Now this is one wild story. The amount of lawsuits coming down the pipeline with stories like this is going to be astronomical.

Gemma 4 26B-A4B is now ~2x faster at 375K context with TurboQuant on MLX-VLM v0.4.4 🚀 The model's official max context is 262K but I pushed it to 375K anyway. That's roughly 5–6 full novels (the entire LOTR trilogy + The Hobbit). Up to ~20K tokens they're neck and neck, but

Batman: The Animated Series achieved its iconic “dark deco” look by painting backgrounds on black paper instead of white.

An average picture that you save on your phone or PC has a size of around 400 kilobytes. It doesn't do anything, it's just a static image. Now divide that by the factor 10, so you drop to 40 kilobytes. That's the size of The Last Ninja, developed by System 3 and published in

TurboQuant: Open Evals on MLX 🔥 Yesterday I launched mlx-vlm v0.4.4 with major TurboQuant performance improvements. Today, the open benchmark results on MM-NIAH (val, 520 samples) using Gemma 4 26B IT by Google DeepMind on M3 Ultra: → 0 quality loss — 78% accuracy for both

Alongside MM-NIAH I’m also running LongBench-V2 to truly showcase where TurboQuant shines which is large context ( above 60K) Running will take around 24h to complete. Meanwhile, here is a sneak peak of 6 samples across different context sizes. See you in a day or two 🫡

Landscapes by Lehi-based painter Brett Allen Johnson (born 1984)

Inspired by Gustav Klimt

Awesome work by Tom Turney 🔥

Después de mucho tiempo de trabajo intensivo tenemos el catártico placer de compartirles este anticipo al primer episodio de Electro Andes, una serie sudamericana de anime de cyberpunk mitológico seteado en una versión fantástica de los Andes. En las siguientes semanas iremos

This interactive exhibition in Japan

A JAPANESE DEV BUILT AN APP THAT SHOWS A FAT CAT ON THE SCREEN AND FORCES YOU TO TAKE A BREAK.