AI Safety & Security

Foundations to the Agentic Frontier

Author

Surafel M. Lakew

Preface

Published May 27, 2026 (updated: May 29, 2026)

TipStatus — May 2026

Part I (Foundations) is now available. Parts II (Topics) and III (Frontier) roll out in weekly increments — check back.

AI Safety & Security is a living, continuously evolving reference for the safety and security of agentic systems — where agentic is the bridge between the two fields: tool-use is the security surface, and autonomy is the safety problem. As systems are increasingly optimized to be agentic, this intersection is where the most consequential and impactful problems now sit.

0.1 What this book is

A distilled synthesis — core concepts, illustrations, and formalizations, not a literature dump. Each entry captures the essential idea, a clear illustration or formalization, and its potential impact or applications. Sources are cited; their full text is not reproduced.

0.2 How to read it

The book is organized by topic (primary axis), chronologically within each topic:

  • Part I — Foundations: a read-once narrative orienting you in the field.
  • Part II — Topics: the living core. Each chapter runs foundations → frontier in chronological order, so a reader can pick up the background needed to engage a recent, technically novel result.
  • Part III — Frontier: rolling intake of the last ~12 months. When a frontier item is superseded or matures, it migrates into its topic chapter — this is what makes the book continuously evolving.

0.3 The field at a glance

AI safety & security timeline Six overlapping eras from pre-2015 foundations to the 2025+ agentic frontier, each linking to a topic chapter. Foundationspre-2015 · inverse RL Adversarial ML2014–19 · robustness Alignment Era2019–22 · RLHF, CAI Interpretability2022–24 · circuits Oversight2023–25 · weak→strong Agentic2025+ · safety × security time → 2026 · today

Each topic chapter expands one thread of this timeline in depth.