This week I built a Source Engine style input/output (I/O) system for level scripting in Sleight of Hand, and if you don’t know what that is or means, you have that in common with most game developers. (Update: It is now available). It’s an astonishingly useful thing to have on any game with level scripting (it’s how Valve’s games do it all the way from Half-Life to Half-Life Alyx). It’s empowering to level designers, and the time and work it stands to save you is unquantifiable but immense. It’s also simple and easy! I’m gonna jot down here how mine (in Unreal) works, but also make a case for the feature in the first place, because like all the most impactful good ideas, most people don’t see the point right away. Alas, I fear I will have to use headings.
Yet Another Incremental Game But This Time About Coding
95❤ 2.7⭐ | by Poptocrack Yet Another Incremental Game (But This Time About Coding) is an idle clicker where your keyboard is your greatest weapon. Don’t worry, you don’t need to know how to code. Just roll your head on the keys, and watch characters magically appear as your projects take shape. There’s no “The End” (yet), but there’s always more code to generate, more upgrades to unlock, and more progress to chase. Features: Mash keys, spawn code – type anything (or nothing that makes sense) and your code grows. Hire AI assistants – automated helpers who type for you, so you can lean back. Recruit AI uber agents – specialists for one specific task, boosting production even further. Take on client projects – earn rewards by coding for imaginary customers. Unlock upgrades and achievements – keep pushing your efficiency to absurd levels. Idle progress – your AI keeps coding even while you’re away. Light narrative flavor – quirky messages and hints of a bigger mystery add some personality. Whether you’re here for the numbers going up, the absurdity of mashing your keyboard, or the dream of an AI-powered dev empire, this game delivers the core incremental loop fans love.
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.
The control layer for AI
The industry spent two years teaching LLMs to speak JSON. That work mattered: free-form text was unusable in production. Today, every serious inference provider uses some implementation (often open-source) of structured output. Structured output has become essential infrastructure that the team at .txt is proud to have spearheaded. Even as the ecosystem evolves, and open-source alternatives emerged, our engine remains the state of the art.
The control layer for AI
The industry spent two years teaching LLMs to speak JSON. That work mattered: free-form text was unusable in production. Today, every serious inference provider uses some implementation (often open-source) of structured output. Structured output has become essential infrastructure that the team at .txt is proud to have spearheaded. Even as the ecosystem evolves, and open-source alternatives emerged, our engine remains the state of the art.
Script Wizards
A TTRPG and software studio. Small tools for running games, and a zine for hackers who play them.
where good ideas come from (for coding agents)
(and the part where users have to level up)
can1357/oh-my-pi
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
bytedance/UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Stories | Cyrus
Insights, tutorials, and case studies on AI-powered development workflows. Learn how teams use Cyrus with Linear and Claude Code to ship 20x faster.
Structured Outputs with Will Kurt and Cameron Pfiffer - Weaviate Podcast #119!
"Design, Composition, and Performance" by Rich Hickey (2013)
"Design, Composition, and Performance" by Rich Hickey (2013)
Everything is ugly, so go build something that isn't — Raiza Martin, Huxe (ex NotebookLM)
The Level Design Book
The Level Design Book gathers level design knowledge for 3D video games in an approachable, up-to-date, and critical way. It is for designers of all experience levels and game engines.