Weird projects I shipped with AI

2026-05-31 · Source: All posts - seangoedecke.com RSS feed · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Gaming & Interactive Media · Depth: Intermediate, short

Summary

An author showcases several personal projects developed with significant AI assistance over the last twelve months, arguing that AI lowers the barrier to shipping unique applications, even if it hasn't yet produced a flood of AI-generated companies. Key projects include Skifreedle, a daily game inspired by Windows SkiFree, where AI facilitated complex feature development and extensive UI theme experimentation. Autodeck, an automatic Anki card generator, attracted over 500 users and covered its operational costs, with AI simplifying deployment and payment integration. The Endless Wiki, an AI-generated wiki with over 280,000 pages, demonstrated a novel non-chat LLM interface, requiring JavaScript to manage inference budget from scrapers. Additionally, a VicFlora Offline PWA was created to cache a plant identification database for field use, a task deemed too complex without LLM help due to difficult data scraping. Other contributions include a gh-standup GitHub CLI extension and an image geolocation benchmark.

Key takeaway

For software engineers or entrepreneurs aiming to rapidly prototype and deploy niche applications, AI assistance fundamentally shifts the effort-to-outcome ratio. You should utilize LLMs not just for code generation, but for overcoming deployment friction like database setup, payment integration, and complex data parsing. This enables you to ship a higher volume of experimental projects, validate ideas faster, and explore novel interaction models that would otherwise be too time-consuming to pursue manually.

Key insights

AI significantly reduces the effort to conceptualize and ship novel, niche software projects.

Principles

• AI assistance enables shipping projects that would otherwise remain unstarted or incomplete.
• LLMs streamline complex tasks like data scraping and UI experimentation.
• Non-chat LLM interfaces offer unique interaction paradigms.

In practice

• Use AI to rapidly prototype and iterate on UI designs.
• Employ LLMs for challenging data parsing and integration tasks.
• Explore non-chat interfaces for LLM-powered applications.

Topics

• AI-assisted Development
• LLM Applications
• Rapid Prototyping
• Web Game Development
• Spaced Repetition
• Progressive Web Apps

Code references

• sgoedecke/skifreedle
• sgoedecke/gh-standup
• sgoedecke/ai_geolocation
• sgoedecke/skills
• basicallydan/skifree.js

Best for: AI Engineer, Software Engineer, Entrepreneur

Related on AIssential

• Building AI with AI — LLMs should be used to build systems, not as systems, reinforcing code's critical role.
• Beyond the Chatbot: Navigating the Industrial Revolution of AI with Awesome-LLM-Apps — "awesome-llm-apps" provides full-stack blueprints to accelerate LLM application development, moving from model discovery to engineering.
• Helping people write code again — LLM-assisted coding empowers experienced individuals to resume programming by reducing time barriers.
• LLM Vs AI: A Practical Guide to Differences, Use Cases, and Tools — Generative AI and LLMs are transforming enterprise operations through diverse applications, requiring careful selection and deployment.
• LLMs and new programming languages: Complementary or Conflicting? — LLMs rapidly adapt to and support new programming languages, accelerating their adoption and reducing learning friction.
• How to vibe code in science: early adopters share their tips — Vibe coding with LLMs enables rapid code generation and application development through conversational prompts, democratizing complex programming tasks.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by All posts - seangoedecke.com RSS feed.