This is a follow-up to my previous post where I covered reducing token costs in a multi-agent pipeline. That post touched on local model fallback at a high level. This one goes deeper on how the routing layer actually works.

The Pipeline

I have five agents, split across two tiers …

Running a multi-agent pipeline for security research gets expensive fast. I have several agents doing sequential analysis work - reading commit diffs, running adversarial bypass analysis, building proof-of-concept exploits. Token costs compound at every step: system prompts, tool schemas, conversation history, and verbose outputs all stack up before a single useful …

I have been pretty facinated with type promotion bugs in the recent months. Why? Because I love when there is some crazy mixed data types with arithmetic. Something about math (in)correctly implemented always makes me geek out. For those not familiar with Type promotion, it's when data type values …

Distracted..

This post is more about a side quest, as I was a bit distracted awaiting some responses on some UAF and Format string vulnerabilities submitted to a couple bug bounty programs.

In order to keep momentum going and my thirst for knowledge well fed with regards to vulnerability discovery …

Introduction to My Chronicles

If you've been keeping up with my adventures, you know I've dived back into low-level vulnerability discovery and research. Recently, I took some time to refresh my understanding of low-level code (assembly) and architecture review, particularly of ARM systems. Given that most systems I work on …