Writing
Notes on LLMs, side projects, and making technology more accessible.
I built a free medical evidence retrieval API
HYFL RAG: free retrieval API over Wikipedia medical articles. No signup, no credit card. Built for LLM agents.
I trained a 1.5B model to deobfuscate Python. It scored 93% and survived the obfuscated Python Olympics.
SemRec: a 940MB fine-tuned Qwen2.5-Coder model that recovers clean semantics from obfuscated Python. 93.36% overall, 11/11 on competition-grade obfuscation.
PetLM: teaching a tiny language model to be a virtual pet
A 25M parameter model, a strict little DSL, and a browser toy that runs locally with WebGPU or WASM.
Self-hosted SMS gateway with an old Android phone
How I built a self-hosted SMS gateway using a spare Android phone, a custom FastAPI relay, and Tailscale for secure, zero-cost text messaging from my AI agent.
educated.space — AI-Powered Educational Resource Generation
AI-powered K-12 educational platform. Generates curriculum-aligned worksheets, quizzes, and info sheets. Live at https://educated.space
Fixing Quran Audio Segment Timings with WhisperX
How I used WhisperX forced alignment to fix inconsistent word timings in a Quran reading app.
QuranZen: A Hybrid Architecture Quran App
Building a full-stack Quran exploration app with React 19, FastAPI, and a hybrid database design.
Running LLMs on a Steam Deck in 5 minutes
A step-by-step guide to setting up your Steam Deck to run local Large Language Models (LLMs) using llama.cpp and a Distrobox container.
Fine-tuning a 3B Model for Transcript Analysis: Better Than 70B Models?
How I fine-tuned Llama 3.2 3B to process transcripts locally, achieving better results than models 5-8x larger through specialized training.
ToddlerTones: offline, toddler-proof soundboard
Designing and building a distraction-free Android app in Kotlin/Compose with low-latency audio and a gentle 'Find it' game.
Reluctant Buddha: Fine-Tuned LLM for shitty insights
Turning a 1B LLM into a deranged cosmic entity running on CPU only.