-
Guardrails with a small model: filtering output on your own machine
A 12-weight classifier plus 4 rules blocked 2 injection attempts and 2 secret leaks, and let 2 legitimate questions through. Runs in pure Python, no large model, no cloud. Granite Guardian 2B is Apache 2.0; llm-guard is MIT.
-
How do you store a secret in an environment variable without leaking it?
A .env file with mode 600, a git ignore rule and masked reading cover most leaks. The script tests this by itself.
-
How to harden SSH: what to turn off and what to keep
Turn off password, root and X11; require a public key. The rest is limits and ciphers. sshd_config line by line.
You reached the end. Every post is here.