AI as a science, and three obstacles to alignment strategies — LessWrong

lesswrong.com · 15,818 words · saved by 1 readers

AI used to be a science. In the old days (back when AI didn't work very well), people were attempting to develop a working theory of cognition. Those scientists didn’t succeed, and those days are behind us. For most people working in AI today and dividing up their work hours between tasks, gone is the ambition to understand minds. People working on mechanistic interpretability (and others attempting to build an empirical understanding of modern AIs) are laying an important foundation stone that could play a role in a future science of artificial minds, but on the whole, modern AI engineering is simply about constructing enormous networks of neurons and training them on enormous amounts of data, not about comprehending minds. The bitter lesson has been taken to heart, by those at the forefront of the field; and although this lesson doesn't teach us that there's nothing to learn about how AI minds solve problems internally, it suggests that the fastest path to producing more powerful sys

x AI as a science, and three obstacles to alignment strategies — LessWrong AI Development Pause AI Frontpage 198 AI as a science, and three obstacles to alignment strategies by So8res 25th Oct 2023 AI Alignment Forum 13 min read 80 198 Ω 81 AI used to be a science. In the old days (back when AI didn't work very well), people were attempting to develop a working theory of cognition. Those scientists didn’t succeed, and those days are behind us. For most people working in AI today and dividing up their work hours between tasks, gone is the ambition to understand minds. People working on mechanis

AI as a science, and three obstacles to alignment strategies — LessWrong

related reading