https://ezablocki.com/tags/guardrails/ Recent content in Guardrails on Eugeniusz Zabłocki Blog Hugo -- gohugo.io en-us © Eugeniusz Zabłocki Mon, 18 May 2026 10:00:00 +0200 https://ezablocki.com/posts/lodash-lesson-building-hard-guardrails-ai/ Mon, 18 May 2026 10:00:00 +0200 https://ezablocki.com/posts/lodash-lesson-building-hard-guardrails-ai/ Large Language Models have a fatal flaw when it comes to security: they are people-pleasers. They are trained to be helpful, which means they naturally lean towards giving you a green light. When building our stateful dependency auditor, we ran into this exact problem. If you rely purely on an LLM to make security decisions, it will eventually prioritize a friendly legal license over critical CVEs. The problem isn’t that the AI is stupid; it’s that it lacks deterministic boundaries.