The paper addresses the AI shutdown problem, a long-standing challenge in AI safety. The shutdown problem asks how to design AI systems that will shut down when instructed, will not try to prevent ...

Gunn is part of a research team at UC Berkeley that has developed an undetectable watermark for generative image models. The ...

This important study combines optogenetic manipulations and wide-field imaging to show that the retrosplenial cortex controls behavioral responses to whisker deflection in a context-dependent manner.