Fast, robust, accurate diffing
joxeankoret/diaphora
Diaphora, the most advanced Free and Open Source program diffing tool.
Anki with Uncertainty - Quantified Intuitions
Turn any flashcard deck into a calibration training tool
heerich.js
Tiny engine for 3D voxel scenes rendered to SVG — boolean ops, oblique/perspective cameras, zero dependencies.
The frontier is open-source today
GLM-5.2 - open weights - single-shot our AI-resistant backend take-home to a higher level than Opus 4.8, and built offmute-v2: state-of-the-art timestamp-accurate diarization. A head-to-head with no detail glossed over.
Pieter Omvlee on Twitter / X
Payed a bit with Jev today. First one of many experiments today in @elyxdesign. Jev is great at classifying data - so it can figure out where my icons should live and keep them organised so I don’t have to pic.twitter.com/Islh7svP39— Pieter Omvlee (@pieteromvlee) September 21, 2026
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
For anyone who has been (inadvisably) taking my pelican riding a bicycle benchmark seriously as a robust way to test models, here are pelicans from this morning’s two big model …
DR Group
For high-dimensional data, dimensionality reduction (DR) methods have been invaluable tools for human understanding, as they can map datasets into two or three dimensions for visualization, providing an intuitive way to understand the data. In recent years, tons of DR methods for data visualization have been proposed, and some are much better than others. In this blog post, we explore several DR methods, discuss how to determine which methods are effective, and explain why some are better than others.