Interplanetary macroeconomic simulator with RPG and turn-based strategy elements
Built with: TypeScript, React, React Native, Nx, Three.js, React Three Fiber, NestJS, WatermelonDB, MongoDB
Deployed using: Docker and Fly.io
Principles: Cross-platform (web + native mobile), offline-first
General purpose achievement tracker
Built with: TypeScript, React, React Native, Nx, NestJS, WatermelonDB, CouchDB, Keycloak
Principles: Self-hostable with Docker Compose, Cross-platform (web + native mobile), offline-first
Apr 24th ◆ end ◆ working on moving the camera between opposite poles [hexasphere]
Apr 24th ◆ Generative AI with Large Language Models
I just started a course on generative AI and LLMs offered by Coursera. The first few videos are an introduction to the use cases and theory of LLMs. Topics covered include the business applications of LLMs, overview of terminology like "transformers" and "fine-tuning a model", and type of LLMs (Llama, GPT, etc.). Overall, this session described the types of interactions humans have with LLMs (inputs and outputs) and the types of tasks LLMs are proficient at performing.
One particularly interesting topic covered was "attention weights". At a high level, "attention weights" enable an LLM to encode/decode complex language constructs (like the relevance of certain words in relation to other words in a sentence)