h1: A Taste of the Bitter Lesson in Automated Theorem Proving Paper • 2610.35962 • Published 12 days ago • 20
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols Paper • 2510.09462 • Published Oct 10, 2025 • 6
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Paper • 2410.22366 • Published Oct 28, 2024 • 82
Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols Paper • 2510.09462 • Published Oct 10, 2025 • 6
Rapidata/117k_human_coherence_flux1.0_V_flux1.1Blueberry Viewer • Updated 2 days ago • 4.5k • 158 • 14