Technical insights and random musings around AI security
Anthropic and Google DeepMind both hit the same wall: detection-based AI controls have a non-zero miss rate and don't scale with agent autonomy. The missing layer is a deterministic, bounded trust layer — enforced at effect boundaries, not chasing infinite patterns.
The core challenge is that you can't enumerate every malicious prompt. But we've solved this exact class of problem before in distributed systems—by defining what IS allowed and enforcing it at the boundaries.
In analyzing over 100 MCP repos, we discovered vulnerabilities tradiontal tools miss -- flaws that live not in code, but how AI systems are architected, reason and interpret natural language prompts
Establishing security boundaries when the LLM tool calling attack surface is expanding faster than solutions can keep up
Security teams are trying to wrap yesterday's controls around today's AI agents—and it's not working. The gap between product security and security products will only be exaggerated by agentic AI.
Exploring why traditional reactive security approaches are inadequate for AI agents that can autonomously compromise systems at machine speed
Introducing our blog where we'll share insights on AI security and cryptographic verification
