~/research
Research Notes
Weekly notes on threat intelligence, LLM security, red teaming, and AI. Published every Sunday. Raw and unfiltered, this is my working log.
Many-Shot Jailbreaking and What It Means for Enterprise LLM Deployments
Spent most of this week working through Anthropic's many-shot jailbreaking paper. The core finding is more significant than the headlines made it sound.
2026 Kickoff: What I'm Building and What's Coming in AI Compliance
Starting the year with a clear focus: ProvStamp for EU AI Act compliance, ThreatWatch v2, and why the August deadline is closer than most people think.