Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills Paper • 2508.19500 • Published Aug 27 • 2
Favicon Trojans: Executable Steganography Via Ico Alpha Channel Exploitation Paper • 2507.09074 • Published Jul 11 • 6
AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding Paper • 2503.01063 • Published Mar 2 • 5
Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal Tests Paper • 2502.06867 • Published Feb 8 • 1
The Impossible Test: A 2024 Unsolvable Dataset and A Chance for an AGI Quiz Paper • 2411.14486 • Published Nov 20, 2024 • 7
Language Models And A Second Opinion Use Case: The Pocket Professional Paper • 2410.20636 • Published Oct 27, 2024 • 2
