On April 22, 2024, Dan Hendrycks of the Center for AI Safety visited the Lab for his seminar, “AI and Evolution.”
For billions of years, evolution has driven the development of life, including humans. Evolution endowed humans with high intelligence, which allowed us to become one of the most successful species on the planet. Today, humans aim to create artificial intelligence systems that surpass even our own intelligence. As artificial intelligences (AIs) evolve and eventually surpass us in all domains, how might evolution shape our relations with AIs? We argue that AI development could be shaped by competitive pressures, giving rise to AI agents that automate human roles, gain power, and deceive others. More abstractly, we argue that natural selection operates on systems that compete and vary, and that selfish species typically have an advantage over species that are altruistic to other species. To counteract these evolutionary pressures, we consider interventions such as carefully designing AI agents’ intrinsic motivations, introducing constraints on their actions, and institutions that encourage cooperation. These steps, or others that resolve the problems we pose, will be necessary in order to ensure the development of artificial intelligence is a positive one.
Dan Hendrycks is the founder and executive director of the Center for AI Safety. He received his PhD in AI from UC Berkeley. He has contributed the GELU activation function (the most-used activation in state-of-the-art models including BERT, GPT, Vision Transformers, etc.), benchmarks and methods in robustness, MMLU, and an Introduction to AI Safety, Ethics, and Society.
