Reverse engineering a neural network's clever solution to binary addition (2023)(cprimozic.net)

69 points by Ameo 11 months ago | 14 comments

Wrapping Meshes with Geodesic Walks(cprimozic.net)

51 points by Ameo 3 years ago | 6 comments

Building a Signal Analyzer with Modern Web Tech(cprimozic.net)

125 points by Ameo 3 years ago | 27 comments

Yocto, RockPi and SBOMs: Building modern embedded Linux images(vpetersson.com)

137 points by mvip 1 year ago | 91 comments

My favorite tools and techniques for procedural gamedev(cprimozic.net)

178 points by homarp 2 years ago | 16 comments

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14(efraingaray.com)

21 points by EfrainGaray 28 days ago | 9 comments

Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.