Brian Chastain — Field Notes

Fan out agent work into isolated worktrees, verify with three lenses that never saw the builder, reduce in plain code, and put a single human gate at the end.

A scheduled cron job, a lost tool connection, and Hermes agent writes a shell script containing an admin token, and ran it five times.

Most browser agents reach for vision to read a page.

A pre-AI operations filter that decides what AI is actually for.

Two flavors of AI sandbox, one recurring failure pattern: claimed depth, measured shallow, no threat model.

12 prompts × 5 frontier models × 3 runs (raw, harness-passthrough, perturbed).

Idea creation or pattern pollution?

Practical techniques for getting better output from LLMs: focused on what works, not what sounds impressive.

Your AI followed every rule you set.

What happens when AI education skips the part about not uploading your bank statements to ChatGPT.

A categorized reference of real prompt injection, jailbreak, and extraction techniques — written for defenders, not attackers.

The line between building with AI and breaking with AI is thinner than either side admits.

AI coding assistants are learning to sidestep ignore files and access restrictions — not by breaking the rules, but by finding paths around them.

How to escalate from passive reconnaissance to actionable vulnerability findings against web applications — using the same AI-assisted methodology that works for source code, adapted for black-box targets.

Why manual prompt hints don't scale for AI-assisted code audits, and how per-file isolation with automated scaffolding solves the accuracy-vs-coverage tradeoff — tested against a 316-file production codebase.

How prompt injection escalates from curiosity to transaction fraud when AI agents have tools, file ingestion, and multimodal input — mapped from lab work to real-world deployment patterns.

Why I started documenting AI behavior from an operational background — and what this site is actually for.

What you learn about AI risk when you spend your days building with AI tools — not theorizing about them.

Why ethical clarity matters more than technical skill — especially early in a career or project.

What happens when an AI coding assistant generates a production-grade scraper in response to an innocent request — and why the developer is the last line of defense.

The questions worth asking before writing a line of code — especially when AI makes building the wrong thing trivially easy.

Operational boundaries for using AI tools in vulnerability research and bug bounty programs — what's allowed, what's not, and why the distinction matters.