Common Sense Is All You Need

TL;DR

This paper argues that achieving true autonomy in AI requires integrating common sense—an ability present in all animals—into learning, reasoning, and embodiment across physical and abstract domains. It critiques scaling and traditional benchmarks (ARC, Turing Test, FSD paradigms) as insufficient for autonomy, and proposes a shift to common-sense–centric challenges, starting from tabula rasa, with redesigned software architectures and interdisciplinary collaboration. The authors define concrete components of common sense, discuss theoretical challenges (e.g., the No Free Lunch theorem) in constrained domains, and provide actionable steps including benchmark redesign, new evaluation metrics, and a focus on embodied cognition. The work aims to unlock the societal and commercial value of autonomous AI by ensuring systems can generalize, reason contextually, and act safely in diverse environments.

Abstract

Artificial intelligence (AI) has made significant strides in recent years, yet it continues to struggle with a fundamental aspect of cognition present in all animals: common sense. Current AI systems, including those designed for complex tasks like autonomous driving, problem-solving challenges such as the Abstraction and Reasoning Corpus (ARC), and conversational benchmarks like the Turing Test, often lack the ability to adapt to new situations without extensive prior knowledge. This manuscript argues that integrating common sense into AI systems is essential for achieving true autonomy and unlocking the full societal and commercial value of AI. We propose a shift in the order of knowledge acquisition emphasizing the importance of developing AI systems that start from minimal prior knowledge and are capable of contextual learning, adaptive reasoning, and embodiment -- even within abstract domains. Additionally, we highlight the need to rethink the AI software stack to address this foundational challenge. Without common sense, AI systems may never reach true autonomy, instead exhibiting asymptotic performance that approaches theoretical ideals like AIXI but remains unattainable in practice due to infinite resource and computation requirements. While scaling AI models and passing benchmarks like the Turing Test have brought significant advancements in applications that do not require autonomy, these approaches alone are insufficient to achieve autonomous AI with common sense. By redefining existing benchmarks and challenges to enforce constraints that require genuine common sense, and by broadening our understanding of embodiment to include both physical and abstract domains, we can encourage the development of AI systems better equipped to handle the complexities of real-world and abstract environments.