Research

You've probably noticed something when using AI coding agents like Claude Code, Cursor, or Codex. The model doesn't just answer - it works. It reads a file, writes some code to search through it, reads another file, runs a check, and slowly pieces together an answer. It feels almost like watching someone think out loud. That intuition is important. Because a paper out of MIT CSAIL late last year - quietly titled Recursive Language Models - essentially formalizes exactly that

Believe it or not AI is here to stay. In 2025, we saw a huge spike of Agentic AI Application and AI Agents. Now the question arise is how secure this AI Agents and Applications are? I was reading a research paper by Santiago Díaz, Christoph Kern, Kara Olive from Google in which they presented Google’s Approach for Secure AI Agents. In the Introduction, Google did presented and shared the potential and risks associated with the AI Agents and did mentioned the need for Agent