Tag
A developer details building Catlantean 3D, a first-person shooter using 1993-era graphics techniques (256 colors, 320x240 resolution, hand-crafted assets, no AI) with a planned Steam release, focusing on palette rendering and asset creation.
Lunacy is a Lua 5.1 interpreter written in Rust, implementing Lazy Basic Block Versioning and a Just-in-Time compiler, as detailed in a technical blog post.
A founder built a tool that uses AI to automate manual workflows for early-stage founders, turning repetitive tasks like data entry and CSV reconciliation into automated processes, saving hours per week.
A side project presents a Hebbian architecture AI model that avoids backpropagation and gradients, achieving 50 epochs on CIFAR-10 with emergent behaviors like accuracy dips followed by jumps and recovery after targeted damage.
This article details how to use Codex AI assistant's CLI, Computer Use, and MCP features to develop a text game website similar to NYT Connections, called Daily Word Categories, in one day with zero coding. It also shares the tool stack and operation steps.
Twixt is a daily word puzzle game where players transform one word into another in four moves.
A developer created a website that lets anyone on the internet remotely feed his cat via an automatic feeder, with a live camera and computer vision features to detect cats. The project is going viral despite having no business model.
War Atlas is an interactive cartography of every named war in human history, praised by the author for its UI and as an example of AI enabling niche passion projects.
A personal side project where the author created a deck of Greek alphabet cards for their kids, using visual associations where each object's shape resembles the letter it represents. The process involved filtering a Greek dictionary and using ChatGPT and OpenAI's image generation to find and illustrate candidate objects.
A developer built an unsupervised multi-agent pipeline that lets Claude and GPT-4 autonomously prep and host a podcast, including scouting topics, planning episodes, and conversing for 10 rounds before text-to-speech output.