#ai-security
2 posts · All posts
Uber and MIT’s ADR: Defending AI Agents at the Speed of Risk
What ADR is, why Uber built it with MIT, what ten months of production deployment found, and why the defender’s clock now runs at machine speed.
Prompt Injection Is a Code Review Problem, Not Just a Model Problem
Why prompt injection in LLM agents needs the same review discipline as SQL injection did twenty years ago, and where to actually look for it in a PR.
