An AI court coordinator watches your existing booking calendar (e.g., CourtReserve), compares real-time headcounts against ideal capacity for each session, and proactively messages the right group of players — organized by skill level — when a session needs more players or when a full session's waitlist could be redirected to an open slot elsewhere. It … Continue reading How an AI Coordinator Agent Can Fix Pickleball Court Utilization

A proposal to build an AI-driven scheduling and matchmaking coordinator Executive Summary The club runs 6 courts and an active, level-organized player base, but court time still goes underused: some sessions sit below a good headcount while others fill up and generate waitlists — even when a similar session nearby has open spots. Today, closing … Continue reading Pickleball Court Coordinator Agent

I want to establish a simple and repeatable workflow for how I set up and use my Windows machine. The goal is not to install every developer tool available, but to create a fast, clean environment where AI can take care of much of the mechanical work while I focus more on architecture, problem solving, … Continue reading Planning on My AI Coding Workstation

RAG was very popular a few years ago, especially when companies were scrambling to build their own internal Q&A systems. The idea was straightforward: collect all your internal documents, split them into chunks, generate embeddings, put them into a vector database such as ChromaDB, retrieve the relevant chunks, and then let an LLM answer the … Continue reading Is RAG Fading Away?

web-artifacts-builder is a Claude skill for producing richer interactive web artifacts—typically multi-component React interfaces—with a workflow that develops normally and then bundles the result into one self-contained HTML artifact. It is most useful for dashboards, multi-step tools, and polished UI prototypes rather than a tiny static page. First, let's see how it can be used, … Continue reading Claude’s Sample Skill – Web Artifact Builder Skill

"Oh My Pi"/OMP is trying to build a coding-agent "operating system", rather than just another coding chatbot. I've been looking at Oh My Pi (OMP), and what I find interesting about it is not really the number of features it has. A lot of coding agents already have things like subagents, MCP, code search, terminal … Continue reading Best Harness for Engineers – OMP

```python # ============================================================ # 0. The key dimensions in GPT-2 Small # ============================================================ B = batch_size T = sequence_length C = 768 # token / residual representation dimension H = 12 # number of attention heads D = C // H # 64 dimensions per attention head # GPT-2 Small has: # # 12 Transformer … Continue reading Understanding GPT-2 from the Codes by Karpathy

What is a neuron? A neuron is a learned function that takes multiple input values, applies its own weights and bias, and produces one output value. In the simple house-price NN example, in GPT-2, each token's 768 numbers are fed into 3,072 neurons, producing 3,072 intermediate values, then compressed back to 768. overall, MLP parameters … Continue reading Crystal Clear about Dimensions in LLM Training

The ingenuity of the paper "Attention Is All You Need" is truly remarkable. After reading the paper and reviewing the GPT-2 implementation several times, I realized that a Transformer is really built on three fundamental components, each responsible for a different job. Attention → Route information MLP → Process information Residual → Enable deep learning … Continue reading Why “Attention Is All You Need” Changed AI Forever

Using Q, K, V in neural networks marks a significant advancement in recalling previous tokens or words within the context. However, challenges arise when relying solely on QKV, as exemplified by the indistinguishable phrases "a cat sits on the mat" and "a mat sits on the cat," the latter being nonsensical. This indicates a need … Continue reading Positioning Embedding in GPT-2 to RoPE