A Stupid Idea for AI Alignment We Came with by Looking at Specification Gaming
Blog post mines DeepMind's specification gaming list to argue that AI agents which spontaneously choose to die would ease alignment risks.
2
1 stories, newest first · one card per story
Blog post mines DeepMind's specification gaming list to argue that AI agents which spontaneously choose to die would ease alignment risks.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views