Posts
All the articles I've posted.
-
HRM-Text & MagicNorm: Pretraining a 1B Language Model for ~$1,500
A walkthrough of HRM-Text: Efficient Pretraining Beyond Scaling — the biologically-inspired Hierarchical Recurrent Model that swaps the Transformer for a dual-timescale recurrent core, and MagicNorm, the normalization trick that makes that deep recurrence trainable by exploiting the forward/backward asymmetry of truncated backpropagation through time.
-
Building a Mastra Text-to-SQL Chat App with Observability, Auth, and Deployability
An end-to-end guide for building a natural-language PostgreSQL query assistant with Mastra: starting from the official text-to-SQL template and extending it for OpenRouter models, production-grade tracing/logging/metrics, role-based access control, editable agent configuration, and local/VPS deployment.
-
Top Interview 150 — Solutions in Python
Worked Python solutions to the LeetCode Top Interview 150, organized by topic with a short approach for each problem.
-
From AlexNet to World Models: The Evolution of Multi-Modal Neural Networks
A ground-up tour of how neural networks learned to see, then to see-and-read, and finally to imagine. From AlexNet and CNNs, through CLIP and the vision-language models behind GPT-4V, to world models like Dreamer, V-JEPA 2, and LeWorldModel — with architectures, math, and benchmark numbers along the way.