The Prompt & The Ponder

Interpretability After the Transformer: We Changed the Architecture and Kept the Microscope Moonshot published Kimi K3's weights on 26 July. 2.8 trillion parameters, 16 of 896 experts firing on any given token, a million-token context, and an attention me…

The Math Remembers: How to Catch a Model Lying About Being Original In June 2026, the city of Rio de Janeiro shipped an AI model and called it its own.

Bounded Wrongness: A Field Guide to Probabilistic Data Structures Your database keeps a perfect index of every key it holds.

The Rest of the Crate: Tempo, Key, and Never Stranding a File Part 1 was the interesting problem: the genre that lived nowhere except in the audio, and the silent ML bug that came with computing it.

Your Music Has No Genre: Reading It Off the Waveform I wanted my Spotify playlists as local files, sorted into a tree my DJ software can read: genre on the outside, tempo band on the inside, hard techno/140-147/.

Your Coding Agent Has Amnesia: It's the Harness, Not the Model The same model that fixes a bug in twelve seconds will, three hours into a refactor, confidently reintroduce the bug it fixed in hour one.

Memory as Polynomial Projection: The Mathematics of Long-Context Predictive Modeling The most-cited result in the SSM-vs-Transformer debate is Repeat After Me [1], which proves that state-space models with fixed-size hidden state cannot copy strings of un…

Energy-Based Transformers: The 1982 Architecture Finally Got Compatible Training Tricks In July 2025, Alexi Gladstone and his collaborators put a paper on arXiv claiming that a neural-network idea first written down in 1982 scales 35% faster than the mode…

The Open Source AI Lie: Weight-Washing, Broken Definitions, and Who Benefits Meta says Llama is open source.

The Post-Transformer Era: State Space Models, Mamba, and What Comes After Attention What if the most important architectural innovation since Transformers isn't trying to replace attention — but to escape its quadratic scaling problem entirely?

VLA Models Demystified: How Robots Learned to See, Listen, and Act What happens when you take a language model and give it a body?

JavaScript Date Is Broken.

Open Source Sunday: Open Source Health Tools That Don't Sell You Out Every fitness app promises to help you "reach your goals."

Context-Free Grammars Weren't Invented in the 1950s Every computer science student learns Backus-Naur Form.

Towards Autonomous Edge AI: Local LLM Inference, Efficient Quantization, and Hybrid Memory in Practice What if your AI worked offline, kept your secrets, and actually remembered you, without ever flinching at a spotty network?

Building Truly Offline Apps Isn’t Magic: Local-First with Next.js, Flutter, and On-Device AI Starting a new app, most of us wire up the backend before we even sketch the core screens -- then hope our offline mode "just works later."

Flutter, But Organized: A Starter Template That Won’t Make You Cry in Debug Starting a new Flutter project can get messy, fast.

Cognitive Debt: Or, How I Forgot Why My Code Works I've been "vibe coding" for a while now.

JavaScript Dates Don’t Have to Be a Nightmare Anymore: Meet Temporal Working with JavaScript's built-in Date object has always felt like defusing a bomb with oven mitts on.

Installing Flutter on Arch: A Choose-Your-Own-Adventure Saga Installing Flutter on Arch Linux is one of those tasks that sounds straightforward until you actually try it.