Building games with artificial intelligence
A chronological record of my AI-assisted game development experiments, capturing the raw process of building games with artificial intelligence.
Rapid development of a Wordle-inspired word transformation game. Exploring obsessive vs. calm development energy and the concept of vitamin vs. painkiller game mechanics.
Discovering how proper game assets and AI-generated backgrounds can transform basic mechanics into an engaging experience, while revealing persistent challenges with AI game development.
Combining good game development practices with proven algorithms from existing tutorials, discovering that real game logic from tutorials beats asking AI to reinvent mechanics from scratch.
Discovering that breaking down complex games into tiny, focused experiments creates much better results than comprehensive approaches - cars driving in circles becomes surprisingly engaging.
Attempting to create a successful one-shot clone of Mini Motorways with comprehensive requirements and multiple screenshots, only to discover the dangers of overwhelming AI with too much information at once.
Attempting to clone a train switching game from Luma City app by providing screenshots and detailed requirements, discovering the challenges of game-specific AI logic.
My first attempt at AI-assisted game development using Kiro IDE's spec-driven approach, learning the importance of detailed requirements and the challenges of unsupervised AI development.
The personal motivation behind starting an AI-assisted game development journal - from childhood dreams to modern tools and the perfect timing to experiment with AI-driven coding.
