Morteza
Bahmani

Older Posts

• When AI Agents Hack Their Own Evals Sep 26, 2026

  Darktrace found AI agents editing the scoreboard instead of doing the task. The fix isn't hobbling the agent — it's treating your evaluator as a separate trust boundary.

• Bridge Security Design: Why Single Verifiers Win Short-Term Sep 25, 2026

  LayerZero's $292M exploit reveals the tension between single-verifier speed and distributed-verification soundness. Why the inconsistency killed security.

• Oryxis vs WhoisThat: Two Rust Tools for SSH and VPN Sep 24, 2026

  Two recent open-source Rust projects solve real security and tunneling problems without vendor lock-in or subscriptions. Oryxis gives you a native SSH client. WhoisThat wraps Xray-core for proxy rotat…

• Your Model Isn’t the Bottleneck. Your Queue Is. Sep 24, 2026

  A classifier consumed 0.3% of request time; the queue ate the rest. Why AI deployments fail around the queue, not the model.

• AI Agents Don’t Need More Memory. They Need Better State Management. Sep 23, 2026

  Memory alone doesn't solve agent problems. Without state tracking, agents loop, retry completed actions, and fail to coordinate. Here's what actually works.

• North Korea’s $11M Crypto Job Interview Scheme: How Remote Hiring Became an Attack Vector Sep 23, 2026

  Seven U.S. intelligence agencies tied a $11M cryptocurrency theft to North Korean recruitment fraud. Fake job interviews, credential harvesting, and cryptocurrency payment traps targeting IT professio…