The poster built a game where Grok generates the story narration, and says it outperformed Gemini and GPT for narrative output.
The poster built a game where Grok generates the story narration, and says it outperformed Gemini and GPT for narrative output.
The poster says they built a text-based game where players make choices, roll dice, and face consequences, while Grok acts as the main narrator behind the scenes. According to the post, Grok keeps the game state on track and writes the story the player reads; the human built the game and framed it as a structured demo on their profile.
They report Grok worked much better than Gemini and GPT for narrative output, crediting both its writing quality and fewer refusals around player actions. The thread gives no hard metrics, implementation details, or measured comparison results.
The useful catch is that the post is only a high-level claim and demo pointer, so you would need the profile-linked project for actual build details.
Act as the narrator of a [genre] text adventure set in [setting]. Describe each scene vividly in 2 to 3 paragraphs, keep track of my inventory, choices, and the story so far, and end each turn by asking what I do next. Begin with the opening scene and wait for my first action.
Claude Code got an old DirectX game running on modern hardware, decompiled much of it, built a headless parallel runner, and now writes full level guides with screenshots.
Make pulls contracts from Gmail, Gemini extracts the term and notice period, and a Sheets register emails the owner 60, 30 and 7 days before each deadline.
A self-hosted n8n job reads your calendar, unread email and Notion tasks at 7am and sends one short brief of what matters today.