System Architect · Security Researcher · Photographer
Morteza
Bahmani
Independent creator exploring the intersection of security, infrastructure, and digital craft. Building at Internet Labs.
Blog
Recent writings on security, infrastructure, and the open web
AI Agents Don’t Need More Memory. They Need Better State Management.
Memory alone doesn't solve agent problems. Without state tracking, agents loop, retry completed actions, and fail to coo…
North Korea’s $11M Crypto Job Interview Scheme: How Remote Hiring Became an Attack Vector
Seven U.S. intelligence agencies tied a $11M cryptocurrency theft to North Korean recruitment fraud. Fake job interviews…
Agents Aren’t Chatbots: Why Distributed Systems Matter
AI agents make API calls, manage state, and fail under load. Treat them like distributed systems, not chatbots. Backoff,…
Signed Installers and the macOS Infostealer Myth
Fake Zoom and Slack installers are delivering the Sonoma stealer to Macs. Code signing blocks tampering, not deception. …
cua: Computer-Use Automation at Scale
An open-source framework for cross-OS computer-use agents with built-in benchmarks and fleet infrastructure — protocol-f…
The Myth of Universal VPN Security
Common belief that any VPN provides equal protection ignores implementation differences, transparency, and real-world ef…
Older Posts
Movie Diaries
from Letterboxd Letterboxd
Projects
01 / 04Things I'm building and contributing to
