The Console
Moving into the terminal — the agents live where the work lives, and code becomes disposable material.
gpt-5 and gpt-oss land, and the center of gravity moves to the terminal. A year-long quiet project — rebuilding the working environment around keyboard, terminal, and AI — culminates in Claude Code running inside emacs, two of the workshop's oldest threads finally joined in one tool. Local models generate real code now; single-file Swift turns out to be a scripting language; Mental Models for Mechanical Minds names how to think about the things; and the ROI-threshold argument lands: with agents that read and refactor, technical debt just got cheaper. Code is disposable material — the 2020 disposability aesthetic, five years early, finally meeting its substrate.
The Quarterly Retrospective
The work moved back into the terminal, and some of it moved off the cloud entirely: gpt-oss made local models practical, llama3.2 turned out to be fast enough to matter, and single-file Swift revealed itself as a scripting language nobody had told us about.
The economic finding outlasted the tooling notes. With agents that can read and refactor code, the future cost of messy code and the current cost of unwritten code both shrank — Technical Debt and the ROI Threshold is the issue's spine, and Mental Models for Mechanical Minds is its field manual.
gpt5 is smarter than you are
gpt5 can choose to be so smart it's almost impossible to judge. Lets see how it does on some unanswerable questions and if it can totally replace google.
Code Generation with Local Models
Small, local AI models deliver surprisingly effective results for everyday tasks. Also llama3.2 is surprisingly fast and gpt-oss is surprisingly good.
gpt-5 and gpt-oss
OpenAI’s GPT-5 launch stole headlines, but GPT-OSS quietly made local AI a lot more practical. This post covers what’s new, how to run it with Ollama or LM Studio, and why context size can change your results.
Using repomix to give llm full context
How to use repomix to package your entire codebase into a single file for LLM context, with tips for managing token counts and mise integration.
context7-mcp
Learn how to integrate Context7 MCP server to get up-to-date code documentation for LLMs and AI code editors, enabling real-time access to the latest library and framework documentation.
use playwright mcp to get high fidelity designs
Learn how to integrate Playwright MCP server to enable AI coding agents to interact with web browsers, take screenshots, and validate designs with high fidelity for accurate web development and testing.
Single file swift mini-apps
swift files can be run directly without compiling and without XCode, making it easy to create native UI elements and access all of macOS's APIs. Once you see Swift as a scripting language rather than just an app language, you start wondering what other capabilities are hiding in plain sight.
Dagger and Container Use
Unlock the power of isolated development with Dagger and Container Use—no more worrying about missing dependencies or system conflicts.
Technical Debt and the ROI Threshold
With agents now able to read and refactor code, the future cost of messy code -- and the current costs of unwritten code -- is shrinking. Code is more disposable and experimentation more rewarding.