root@thinkingtokens:~/ideas $

Ideas

Essays, working theories, and perspective on AI, security, and the systems taking shape around us.

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 →