MLX: Machine Learning Built for Apple Silicon
Discover how Apple's MLX framework brings efficient machine learning to Apple silicon. Learn about unified memory, lazy evaluation, GPU acce...
Oct 22, 2026
6 min
I Built the Smallest LLM I Could to Understand How They Work
I use LLMs every day without knowing how they work, so I built the smallest one I could: a tiny transformer that writes Shakespeare one char...
Oct 23, 2026
9 min
What Is an AI Engineer in 2026?
Everyone seems to define the AI engineer job differently. This post explains what the role really involves, how it compares to ML engineer, ...
Oct 9, 2026
5 min
Jev, the AI model that never writes a word
TypeSafe AI's Jev never writes a sentence. It answers typed questions in one parallel pass, with a probability on every answer. Here is how ...
Oct 4, 2026
4 min
Neural Networks, Explained Simply - Part 3: Activation Functions and the Problem with Straight Lines
Part 3 of our Neural Network Series: why depth alone doesn't help without activation functions, how sigmoid and ReLU work in plain language,...
Sep 27, 2026
3 min
Laya: A Fast, Multilingual "System 1" for Structured Decisions
Laya brings fast, structured decision-making to AI workflows with typed outputs for classification, scoring, and yes/no predictions. This de...
Sep 24, 2026
11 min
Building an AI That Never Stops Learning on 8GB of VRAM
Most language models are trained once and frozen forever. mini-AGI is a small byte-level model that keeps learning continuously on a single ...
Sep 21, 2026
6 min
DeepSeek V4.1 Flash Is Out — and It's Coming for Its Own Pro Tier
DeepSeek V4.1 Flash isn't just another model release. Its architecture, tiny KV cache, aggressive pricing, and retirement of V4-Pro point to...
Sep 10, 2026
7 min
Neural Networks, Explained Simply — Part 1: What Even Is a Neural Network?
The first post in our Neural Network Series: how a single artificial neuron works, built from an everyday decision, then stacked into a full...
Sep 9, 2026
4 min