LLM fundamentals: what the papers actually say

RAG: a diagnostic reference for real systems

I trained a 1.5B model to deobfuscate Python. It scored 93% and survived the obfuscated Python Olympics.

PetLM: teaching a tiny language model to be a virtual pet

Self-hosted SMS gateway with an old Android phone

educated.space — AI-Powered Educational Resource Generation

Fixing Quran Audio Segment Timings with WhisperX

QuranZen: A Hybrid Architecture Quran App

Running LLMs on a Steam Deck in 5 minutes

Fine-tuning a 3B Model for Transcript Analysis: Better Than 70B Models?

ToddlerTones: offline, toddler-proof soundboard

Reluctant Buddha: Fine-Tuned LLM for shitty insights