Sign in

AI

30
Sep
Do I Really Need a DGX Spark? Running Local AI for AppSec on a Base M5 MacBook Pro with 32GB

Do I Really Need a DGX Spark? Running Local AI for AppSec on a Base M5 MacBook Pro with 32GB

A base M5 MacBook Pro ran Qwen3.6 35B at 45–57 tokens/sec, fully on its GPU. Here's why I didn't need a DGX Spark to build my AI AppSec pipeline locally.
9 min read
09
Aug
Building an AI-native security pipeline for Stokum.NET

Building an AI-native security pipeline for Stokum.NET

I wrote before about the zero-trust architecture behind Stokum, encrypted tunnels, JWT auth, row-level tenant isolation, no implicit
2 min read