Armore
Blog

Notes from the
people building it

Engineering and security writing about Armore Edge. Read time on every post is computed from the text at 230 words per minute rather than typed in by hand, so a label cannot drift from the post it sits on.

Featured · Engineering

We ran our AI with every socket denied by the kernel. It answered anyway.

Private AI is usually a promise about intent. We wanted one that survives a hostile test, so we ran inference inside a macOS sandbox where the kernel refuses every socket — and measured what came back.

· 3 min read