Quick Updates

Learnings from Open Jarvis

Self-hosting LLM and MCP services is more networking intensive than initially known. Working to update my networking skills to address this by studying for the CCNA exam. I'm tying this into my plan to do more AI/ML self-hosting.

MSAI

This is ongoing, setting …

Updates

1. Infrastructure solved

   Research - even small models are either very RAM or GPU VRAM intensive, with 16GB of VRAM seeming to be the entry point Running locally on my gaming desktop 2. LLM provider selections made

   LM Studio hosting the gpt-oss-20b model locally

2. Core structure being built Choosing to leverage …

The What

I am participating in the OpenAI Open Model Hackathon (repo hosted here) hosted by DevPost for fun and some hands-on experience with self-hosting an LLM, in this case OpenAI's new gpt-oss model.

My project/ submission/ design is built around the idea of leveraging a local, self-hosted LLM to …

Introduction

I've poked at setting up a portfolio page a few times in the past, including once using the Golang based Hugo, but I didn't have the time to set one up properly. However, as I find myself between jobs, completed my first Masters, about a month out from starting …