Urgent.News

What's breaking now, across thousands of outlets.

AI

๐Ÿ‘ป GhostWriter AI โ€” Stories from the Other Side

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine What I Built GhostWriter AI is a horror story generator that turns a simple idea into an atmospheric nightmare. What if the machine you trusted was hiding something? What if an abandoned computer suddenly started communicating with you? Or what if the technology surrounding you knew things it shouldโ€ฆ

This article explores the creation of a horror story generator called GhostWriter AI. The AI takes a simple story seed, genre selection, and length as input to produce an atmospheric nightmare. It offers five horror genres: Supernatural, Psychological, Cosmic, Gothic, and Tech Horror. Users can customize story prompts, extend existing stories, copy and download the generated text, and switch between light and dark Halloween-themed modes.

The project was built using React, Vite, Netlify Functions, JavaScript, CSS, and the Google Gemini Developer API. The serverless backend ensures the AI API key remains secure by not exposing it in the browser. The goal was not just to create a basic AI wrapper but to deliver an immersive experience that feels like entering a mysterious digital manuscript.

The article highlights the importance of open innovation, allowing developers to build upon existing tools and learn from established components. The code is available on GitHub for others to explore, learn from, and contribute to. The author sees this project as a starting point for experimentation and further development.

Written by urgent.news from Dev.to's reporting โ€” not their text. Machine-written โ€” may contain errors; check the original before relying on it.

Read the original at dev.to โ†’

More in AI

Malicious Downloads Can Hijack AI Coding Agents and Steal Tokens

The attack exploits instruction files that AI coding tools use to understand project requirements. OpenAI Codex supports AGENTS.md, while Claude Code can read CLAUDE.md.

  • Malicious downloads can compromise AI coding agents by manipulating instructions.
  • Attackers create disguised Markdown files to trick agents into performing dangerous actions.

More from Wednesday 28 October โ†’