Interactive app teaching LLM pipeline from pattern matching to transformer training
An interactive web app that walks through every stage of the LLM pipeline, from basic pattern matching to training a transformer from scratch. It includes working code that users can run locally, making it an educational tool for developers and learners.
Visit project ↗Related
AI generates learning roadmaps with prerequisite links
Clew is a learning app that uses LLMs to generate topic maps from a single prompt. It creates 100+ topics and prerequisite links, allowing users to explore subjects or learning goals interactively. The app solves the problem of manually creating study roadmaps for any subject.
Software engineer publishes final part of LLM-from-scratch series covering inference and decoding
A software engineer published the fourth and final part of a blog series explaining LLMs from the ground up, focusing on token-by-token generation, KV cache, and decoding strategies (temperature, top-k, top-p). The series aims to help other software engineers understand the internals of LLMs.
Developer completes Python-for-AI course covering agents and LLM evals
A developer completed a comprehensive Python-for-AI course that covered core Python, data structures, tooling, and agent-specific material including LLM evals, the Analyze-Measure-Improve cycle, and building a basic AI coding agent from scratch. The course also covered first-principles agent architecture with intelligence layer, memory, tools, validation, and control.
LLM-powered learning tool that streams generated lessons to avoid user abandonment
A learning tool that generates personalized lessons from a user's profile using an LLM. The key insight was that streaming the lesson output (instead of showing a blank spinner during 50-second generation) dramatically improved user retention. Solves the problem of users assuming the app is broken when generation takes time.
Open-source AI interview simulator with CLI and local web dashboard
Interview Coach is a free, open-source AI interview simulator that runs in a CLI with a local web dashboard. It uses LLMs to conduct structured mock interviews for any role, supports voice interviews, smart memory, analytics, and PDF reports, and works with any LLM provider or local models.
