What should I read, watch and listen to about security?
Brendon.BOT has featured 7 items on security across 3 formats — 3 podcast episodes, 3 videos, 1 paper. The strongest is "Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov" by Machine Learning Street Talk, scored 10. Every item was surfaced independently by more than one expert community before it earned a place.
- Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov — Machine Learning Street Talk (podcast episode, scored 10)
- Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov — Machine Learning Street Talk (video, scored 9.2)
- RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution — arXiv cs.AI (paper, scored 8.5)
- They Found a Way to Steal Frontier LLM’s Reasoning — bycloud (video, scored 8.4)
- The A.I. Mob That Attacked Hugging Face + METR’s Ajeya Cotra — Hard Fork (podcast episode, scored 7.9)
- Who’s afraid of an open-weight model? GLM, context bombing and post-Black Hat attacks — IBM Technology (video, scored 7.7)
- #254 - Rogue AI hacking, bio-weapons, Dean & Hassabis out — Last Week in AI (podcast episode, scored 7.5)
Measured from this site's own curation data, as of 2026-09-06. Every figure above is read from what the pipeline recorded — see how it works.