https://jaipradeesh.com/tags/security/ Recent content in Security on jaipradeesh Hugo en-us Sun, 28 Dec 2025 00:00:00 +0000 https://jaipradeesh.com/posts/llm-discovery-deterministic-execution/ Sun, 28 Dec 2025 00:00:00 +0000 https://jaipradeesh.com/posts/llm-discovery-deterministic-execution/ <p>Run an LLM-based code reviewer on a code change 10 times and it flags a SQL injection vulnerability 7 times. The other 3 runs come back clean. Same code, same vulnerability, different result.</p> <p>LLMs are probabilistic, but security requirements are binary. &ldquo;Usually catches security issues&rdquo; is a bug, not a feature.</p> <p>When LLMs do catch something, the finding is often good because they pick up on subtle, contextual patterns that would be hard to write rules for from scratch. The trick is using them as a discovery layer: have the model find what to look for, then encode those discoveries as deterministic rules.</p>