# LLM.txt - Six Things People Built With GPT-6 Astra: Trains, Games, And Personal Apps ## Article Metadata - **Title**: Six Things People Built With GPT-6 Astra: Trains, Games, And Personal Apps - **URL**: https://www.llmrumors.com/news/gpt-6-astra-community-builds-games-3d-personal-apps - **Publication Date**: September 5, 2026 - **Reading Time**: 7 min read - **Tags**: GPT-6 Astra, OpenAI, Codex, Creative Coding, Game Development, Blender, AI Agents, Developer Tools - **Slug**: gpt-6-astra-community-builds-games-3d-personal-apps ## Summary From editable steam trains to a playable portfolio and an iPod-style Mac app, Astra's early builders are turning personal ideas into software worth exploring. ## Key Topics - GPT-6 Astra - OpenAI - Codex - Creative Coding - Game Development - Blender - AI Agents - Developer Tools ## Content Structure This article from LLM Rumors covers: - Data acquisition and training methodologies - Comprehensive source documentation and references ## Full Content Preview TL;DR: Astra's early builders are making unusually personal things: Tom Krcha reports a steam train with 3,295 editable objects, while Pietro Schirano says he built an iPod-style Mac app for Codex threads in 15 minutes.[1][2] These are creator reports, not controlled tests. The interesting pattern is the output: models, interfaces, and games that invite another change instead of ending at a screenshot. Cover: LLM Rumors conceptual illustration of a maker's workbench. It does not depict the creators' actual projects; their original demonstrations are linked below. A steam train assembled from a drawing. A portfolio folded into a virtual handheld console. A desktop companion that dresses an AI workflow in the visual language of an old music player. The first wave of GPT-6 Astra projects has a welcome sense of play. Our previous Astra analysis focused on what happens when a model can operate software. This time, look at what people actually want it to make. The projects below range from public artifacts to creator demonstrations; they should be enjoyed with that distinction intact. The real story isn't another race to generate the prettiest landing page. It is the possibility that more people can afford to follow a peculiar idea far enough to find out whether it works. OpenAI's launch presentation emphasizes stronger visual judgment across applications, games, and renderings, alongside tools for building and sharing websites.[7] Community projects put a more useful question to that pitch: what becomes worth making when a first version is easier to reach? The Steam Train: A Drawing Becomes Material To Work With Tom Krcha's train is a particularly good place to start. He says Astra reconstructed an old steam-train drawing in Blender as 3,295 editable objects.[1] That number describes the creator's object count. It does not measure engineering accuracy, mesh quality, or readiness for a commercial game. The appeal is more immediate: a reference picture becomes a scene that can be taken apart and changed. For a maker, being able to inspect the result is part of the fun. A wheel can become the next task rather than an unchangeable feature of a generated image. Krcha's follow-up moves the idea into code. He describes two trains generated at runtime using TypeScript and Three.js, with wheel movement and explode-and-reassemble behavior.[8] That is a different kind of creative object: a visual construction whose behavior is part of the artifact. The practical attraction is iteration. Change the proportions, exaggerate a mechanism, or use the scene to explain how assemblies fit together. The demo is a starting point for those experiments, not evidence that technical modeling has been solved. Watch Tom Krcha's original train demonstration. The Personal Interface: An iPod For Your AI Work Pietro Schirano's example brings the same spirit to everyday software. He reports building an iPod-style Mac app that visualizes Codex threads in 15 minutes.[2] The delightful detail is the choice of metaphor. A developer workflow gets the personality of a familiar physical object. That is a useful challenge to the assumption that productivity software must look interchangeable. A personal tool can be deliberately nostalgic, compact, or odd. It only has to make sense to the person using it. Paul Solt offers a quieter companion example: an iOS app for weekly running mileage. He reports 13 minutes and 3 seconds for the initial demo using his AppCreator skill, then 1 hour to reach a fully functional version, with steering between build-and-run turns on his physical iPhone.[3][10] The skill matters because the workflow includes reusable guidance, not just a model facing an empty screen. ... [Content continues - full article available at source URL] ## Citation Format **APA Style**: LLM Rumors. (2026). Six Things People Built With GPT-6 Astra: Trains, Games, And Personal Apps. Retrieved from https://www.llmrumors.com/news/gpt-6-astra-community-builds-games-3d-personal-apps **Chicago Style**: LLM Rumors. "Six Things People Built With GPT-6 Astra: Trains, Games, And Personal Apps." Accessed September 6, 2026. https://www.llmrumors.com/news/gpt-6-astra-community-builds-games-3d-personal-apps. ## Machine-Readable Tags #LLMRumors #AI #Technology #GPT-6Astra #OpenAI #Codex #CreativeCoding #GameDevelopment #Blender #AIAgents #DeveloperTools ## Content Analysis - **Word Count**: ~1,336 - **Article Type**: News Analysis - **Source Reliability**: High (Original Reporting) - **Technical Depth**: Medium - **Target Audience**: AI Professionals, Researchers, Industry Observers ## Related Context This article is part of LLM Rumors' coverage of AI industry developments, focusing on data practices, legal implications, and technological advances in large language models. --- Generated automatically for LLM consumption Last updated: 2026-09-05T16:39:55.382Z Source: LLM Rumors (https://www.llmrumors.com/news/gpt-6-astra-community-builds-games-3d-personal-apps)