notadamking

Writing

Thoughts on AI, systems design, and the craft of building software.

not a newsletter

Weekly-ish dispatches on AI engineering and systems design.

01
AI March 10, 2026 ↗ stoneforge.ai

Why AI Coding Agents Waste Half Their Context Window

AI coding agents burn 20–40% of their context window on inefficient codebase exploration. A hierarchical documentation system cuts orientation from 15–20 tool calls to just 1–3.

10 min read
02
AI March 3, 2026 ↗ stoneforge.ai

Introducing Stoneforge: AI Orchestration Platform

Announcing Stoneforge — an open-source platform that orchestrates multiple AI coding agents in parallel using git worktrees, automated task dispatch, and merge reviews.

8 min read
03
Opinion June 9, 2023 ↗ Medium

The Hidden Crisis in Open Source Development: A Call to Action

Open-source passion is fading as contributions become career stepping stones and corporate talent-scouting tools. A case for systemic change to sustain the ecosystem.

7 min read
04
AI October 15, 2019 ↗ Medium

Trade and Invest Smarter — The Reinforcement Learning Way

Introducing TensorTrade, an open-source Python framework for training, evaluating, and deploying robust trading agents using deep reinforcement learning.

19 min read
05
AI June 7, 2019 ↗ Medium

Optimizing deep learning trading bots using state-of-the-art techniques

Applying feature engineering, Bayesian optimization, and the Sortino ratio reward to push average agent profit to nearly 850% on test data.

10 min read
06
AI April 27, 2019 ↗ Medium

Creating Bitcoin trading bots that don't lose money

Experimenting with deep reinforcement learning and OpenAI Gym to build cryptocurrency trading agents that learn profitable strategies on historical BTC data.

9 min read
07
AI April 18, 2019 ↗ Medium

Rendering elegant stock trading agents using Matplotlib and Gym

Extending a custom stock trading Gym environment with rich, annotated Matplotlib visualizations that update on each step.

8 min read
08
AI April 10, 2019 ↗ Medium

Create custom gym environments from scratch — A stock market example

Building a custom OpenAI Gym environment for simulating stock trades on historical price data using reinforcement learning.

7 min read