← Brown Cyber Services · Red Thread · rev 2026-11-06
I've put together a reading path of 147 papers and posts on AI agents and AI security, in an order that builds. It's for anyone who wants a guided route instead of a pile of links, and your progress and notes stay in your browser.
Reasoning, agent engineering, AI security, misalignment, interpretability, evals, and the practical gaps. Tap a row to mark it read; tap Read to open the local copy.
Curated by Daniel Brown, Brown Cyber Services. Progress and notes stay in your browser; nothing is sent anywhere. Every item links to its source. If you host your own copy, fetch.py can pull personal reading copies of the arXiv papers for the in-page reader and offline mode.
© 2026 Brown Cyber Services Inc · All rights reserved