The State of Multilingual LLM Safety Research: From Measuring the...
Scaling Laws For Scalable Oversight
(A security aspect contrasting Compton might be that tactical versions are initiated to have controlled chain reactions and then vanish, also not unlike Houdini, or a locked Roomba mystery, so there may be a forensic science. Also relate to prior paper on MAIM's version of MAD and articles on quantum hacks.))
An approach to technical agi safety apr 2025
Constitutional Classifiers: Defending against Universal Jailbreaks...
International AI Safety Report 2025
International AI Safety Report 2025
Can Go AIs be adversarially robust?
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
GS levels.