AI Security
Triage Backlog Reduction: Griffin AI vs Mythos
A shrinking triage queue is the clearest sign a security programme is working. We explain why Griffin AI shrinks queues and Mythos-class tools grow them.
Feb 19, 20266 min read
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
A shrinking triage queue is the clearest sign a security programme is working. We explain why Griffin AI shrinks queues and Mythos-class tools grow them.
Fine-tuning an open-weight model sounds like a shortcut to a custom SecOps copilot. In practice, it is one step of a much longer journey.
A benchmark that the model has seen in training is a benchmark of memorisation. Specific leakage-testing methods separate generalisation from recall.
Claude Desktop's MCP support makes it a capable security tool. Griffin AI builds on that foundation rather than competing with it.
An architectural comparison of Griffin AI's engine-grounded reasoning stack against the pure-LLM pattern that Mythos-class products rely on.
MCP supports stdio, streamable HTTP, and a handful of experimental transports. Each has distinct security properties, and the choice of transport constrains every other security decision you make about the deployment.
Multi-modal models bring image, audio, and video into the AI supply chain. Each modality introduces provenance and integrity challenges that text-only pipelines never had to face.
LLM-generated Dockerfiles repeat the same six or seven mistakes. Here is the pattern catalog and how to catch them before they ship.
Function calling gives models the ability to act. Acting safely on behalf of a specific user, in a specific context, within specific policy is a different problem.
Weekly insights on software supply chain security, delivered to your inbox.