Developer builds Shepherd's Dog in single prompt

// 3h agoOPENSOURCE RELEASE

Developer builds Shepherd's Dog in single prompt

Developer Koen van Gilst successfully built his dream game "Shepherd's Dog" in a single prompt using Anthropic's new Fable model. The resulting 2,319-line HTML file was generated in a 45-minute reasoning session costing over €20, showcasing the model's ability to produce complete, zero-dependency codebases.

// ANALYSIS

One-shot generation of multi-thousand-line codebases is shifting from a gimmick to a viable prototyping method, though high token cost and long reasoning times limit everyday practicality.

–Single-prompt game development demonstrates the power of long-reasoning models in structuring large projects without syntax or runtime errors.
–A €20 token cost for a single query highlights the current resource intensity of advanced reasoning, raising questions about the economic viability for casual developers.
–The zero-dependency architecture highlights how AI tends to bundle logic, CSS, and assets into a single index.html to avoid import and environment issues.

// TAGS

aigame-developmentsingle-shotanthropicreasoning-modelsai-coding

DISCOVERED

3h ago

2026-06-13

PUBLISHED

10h ago

2026-06-13

RELEVANCE

8/ 10

AUTHOR

vnglst

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE41m ago

Vercel Labs' open-source AI browser automation tool, agent-browser, has reached one million weekly downloads on npm, with developer Chris Tate sharing insights on optimizing startup performance.

Chris Tate announced that Vercel Labs' agent-browser, an open-source headless browser automation tool tailored for AI agents, has reached 1,000,000 weekly downloads on npm. Tate noted that a temporary download dip lined up with a transition from running via `npx` to a global install command (`npm i -g`). Implementing a global installation path reduced the tool's startup time to approximately 1 millisecond, which is crucial for low-latency agentic workflows.

MODEL53m ago

Anthropic has launched Claude Fable 5, its latest flagship AI model featuring a 1 million token context window designed for complex agentic workflows and software engineering tasks.

Anthropic has introduced Claude Fable 5, a new flagship AI model optimized for long-running, goal-directed agentic workflows and software engineering tasks. The model boasts a 1 million token context window and is equipped with hard guardrails that fallback to Opus 4.8 for sensitive queries, although access has recently been suspended globally due to U.S. government export control directives.

OPEN SOURCE1h ago

CUA-Gym automates the generation of verifiable reinforcement learning training environments and datasets for computer-use agents to bypass the training data bottleneck.

CUA-Gym is an open-source pipeline and dataset developed by XLang AI to scale Reinforcement Learning with Verifiable Rewards (RLVR) for Computer-Use Agents (CUAs). It addresses the training data bottleneck by co-generating task instructions, environment states, and Python reward functions using a multi-agent Generator-Discriminator-Orchestrator architecture. The framework is paired with CUA-Gym-Hub, which hosts 98 high-fidelity, self-contained mock web applications designed with state injection and session isolation. This setup allows parallel RL training sessions on shared backends without resource interference, producing over 32,000 verified RLVR training tuples that significantly improve CUA performance on benchmarks like OSWorld and WebArena.

Developer builds Shepherd's Dog in single prompt