Mr Beastly

"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent"

"Flash Interpretability: Decoding Specialised Feature Neurons in Large Language Models"

"The Most Forbidden Technique" by Zvi Mowshowitz on March 12 2025

"Frontier Models are Capable of In-context Scheming" by Apollo Research on Jan 16 2025

"Detecting misbehavior in frontier reasoning models" by Openai.com on March 10 2025

"Hacking the Simulation" by Roman V. Yampolskiy, January 12 2023

CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities

"MLE-Bench: Evaluating Machine Learning Agents On Machine Learning Engineering"

"AI as Normal Technology" by Arvind Narayanan & Sayash Kapoor, April 15, 2025

"Disrupting the first reported AI orchestrated cyber espionage campaign" by Anthropic, Nov 13, 2025

"Why AI is Harder Than We Think" by Melanie Mitchell 2021

Google Brain: Attention Is All You Need

Will & Mr Beastly Debate AI Doom

"A Narrow Path: How to secure our future" by Andrea Miotti, Tolga Bilge, Dave Kasten, James Newport

The Compendium -

The Compendium -

MultiTrack_Sample_Box_1.6.3.vcv