Bits2Bricks

Technical tutorials bridging software and physical engineering by Yago Mendoza.

- Claude Code from zero to production: The complete Claude Code stack: installation, CLAUDE.md, skills, hooks, permissions, MCP servers, agent teams, Cowork, UI tools, and the workflow that ties them together. - How LLMs learn: A ground-up explanation of how language models are trained after pretraining: SFT, DPO, RL, RLHF, reward hacking, KL divergence, and the DeepSeek-R1 pipeline. - LSTMs from scratch: A patient, ground-up build of the LSTM, from a single neuron to a recurrent circuit with memory. What the four gates do, why we add the cell state, and what the network actually learns to produce. - MCP before and after: The Model Context Protocol turned every external service into a tool call. Here's what changed, what broke, and what's coming next. - The complete OpenClaw playbook: The full OpenClaw stack: architecture, VPS deployment, skills, channels, security, and every containment technique ranked by effort and protection. - Transformers from scratch: A patient, ground-up explanation of transformer architecture: how tokens become predictions, what attention really computes, where facts live, and why it all scales. - Model-based fault detection in a two-tank system: Model-based fault detection and isolation on a two-tank hydraulic plant under closed-loop control. Thirteen component relations are reduced by structural analysis to four analytical redundancy relations, evaluated as residuals on Simulink runs, thresholded on healthy data and matched against a fault-signature matrix. Covers detectability and isolability, the noise cost of differentiating level measurements, the failure of exact signature matching, and the calibration a physical installation would require.