🤖 ai Intermediate
⏱️ 10 min
AI Strategy: Why We Moved from Local Llama to OpenAI
A pragmatic analysis of the costs, performance, and complexity of running local LLMs versus cloud providers, and why we adopted a hybrid architecture.
4 articles found
A pragmatic analysis of the costs, performance, and complexity of running local LLMs versus cloud providers, and why we adopted a hybrid architecture.
Building the ultimate developer portal for the home lab. We integrate 'gethomepage', Spotify Backstage, and secure it all with Authelia SSO.
A comprehensive guide to hardening your homelab environment using ufw, network segmentation with VLANs, and SSH key-based authentication.
Why we abandoned the cloud for bare metal. A deep dive into the cost savings, performance gains of 10GbE, and total data sovereignty of running BlueRobin on-premise.