AI assurance, adversarial evaluation, and off-baseline LLM behavior. Marine intel vet. GRC by trade, model behavior nerd by choice
Popular repositories Loading
-
Sleeper
Sleeper PublicLocal-first agent tool-call assurance lab: injection → tool action → control gate → evidence.
JavaScript
-
ai-threat-field-guide
ai-threat-field-guide PublicAn evidence-based field guide to real-world adversarial AI incidents, emerging patterns, and MITRE ATLAS mappings.
TypeScript
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.