ngxson's blog

A llama.cpp maintainer's personal take on AI coding

What it truly means to be productive in an era where AI can do (almost) everything.

A reflection on the importance of open source software for the society.

An easy-to-follow guide on how to use OCR models with llama.cpp.

My thoughts on the recent news about GGML and llama.cpp joining Hugging Face, and what it means for the Local AI.

My journey into analog photography

Implementing an RF433 gateway using ESPHome and a custom Home Assistant add-on to manage multiple RF433 receivers for my smart home.

Designing a smart home system from electrical wiring to Home Assistant automations, using affordable devices and network-inspired architecture.

Photos from my visit to Oxford and reflections on presenting at OxML Summer School 2025

Keep it simple, stupid!

A simple and easy-to-use wrapper for working with GGML

Join my adventure into the world of llama.cpp and AI vision!

A minimal proof-of-concept demonstrating a vulnerability in Next.js middleware described in CVE-2025-29927

Exploring various formats, including GGUF, Safetensors, PyTorch, and ONNX

Exploring Brussels and FOSDEM 2025: A visual journey through history, open-source AI, and Belgian charm.

A treasure hunt for chestnuts among autumn's golden forest.

Convert any PEFT LoRA adapter into GGUF and run it with any GGUF base model

Explore Retrieval-Augmented Generation (RAG) and create one from scratch to understand the fundamental concepts.

Is it too soon or too late to learn about AI's potential?

A visual journey through Porto: Where history meets modern art