root@thinkingtokens:~ $ open research-notes

AI security research Open-source experiments Independent thinking

Thinking clearly about AI security. Before the playbook catches up.

I’m Nur Gucu. I use a decade of offensive-security experience to study what AI agents trust, how they behave, and how defenders can respond.

background A decade in offensive security
presented research DEF CON 34 open source Creator of ORPHEUS
Illustrated portrait of Nur Gucu currently researching

// behind the terminal

Hi, I’m Nur.

I follow questions until they become something testable: an experiment, a framework, a comparison, or a field note.

The thread running through my work is trust—what agents assume, what systems inherit, and how we can reason about both more clearly.

// research and ideas

Latest writing

For builders, defenders, and curious readers who want the reasoning—not just the conclusion.

research

Where I Drop AI Red Teaming Tips

Not everything I work on needs a full writeup. Some findings are a single technique, a single vector, a single “oh, that’s interesting” moment. Those live somewhere else — a...

ai red-teaming llm tips github
Read article
ideas

The Art of Adversarial Prompting

Traditional offensive security has choreography. You scan, enumerate, find a vector, exploit. Clean. Predictable. There is a playbook — even if it is unwritten — and a decad...

ai red-teaming llm adversarial
Read article

root@thinkingtokens:~ $ subscribe

Follow the thinking.

New research, practical field notes, and carefully argued ideas—sent only when there is something worth sharing.