Common sense
The broad background knowledge about the everyday world that humans use to interpret situations and make decisions, and which AI systems largely lack.
As defined in 94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans
Other definitions
Intuitive understanding of how the world works, including physics, causality, and object permanence; a capability that cats and babies have but current AI systems lack
AI: Grappling with a New Kind of Intelligence | World Science Festival
Where it comes up · 9
- The Shape of AI to Come! Yann LeCun at AI Action Summit 20255 claims
- The Future of Artificial Intelligence4 claims
- 248 | Yejin Choi on AI and Common Sense4 claims
- Gerd Gigerenzer on How to Stay Smart in a Smart World2 claims
- Yann LeCun: Special Lecture on AI and World Models2 claims
- Yann LeCun Says LLMs Have 2 Years Left…1 claim
- Fully autonomous robots are much closer than you think – Sergey Levine1 claim
- AI: Grappling with a New Kind of Intelligence | World Science Festival1 claim
and 1 more
Most important claims · 10 of 21Search all claims for “Common sense” →
- A particularly interesting finding is that systems trained on masked video frame prediction show anomaly detection capability: when the system slides a prediction window over a video, it detects frames where anomalous events occur (objects disappearing, changing shape spontaneously) through sharp spikes in prediction error, indicating the system has learned intuitive physics and common sense despite the simplicity of the training objective.The Shape of AI to Come! Yann LeCun at AI Action Summit 2025
- Common sense is unspoken knowledge about the world that we acquire through experience—knowledge that was never written down as rules because it would be impossible to enumerate all such rules; it includes knowing that a stop sign on a billboard advertisement is not a real traffic stop sign.The Future of Artificial Intelligence
- Current machine learning techniques are fundamentally inadequate compared to human and animal learning because they lack the right characteristics: animals and humans have background knowledge allowing them to learn new tasks extremely quickly, understand how the world works, reason and plan based on common sense, and are driven by objectives—capabilities that current AI systems do not possess.The Shape of AI to Come! Yann LeCun at AI Action Summit 2025
- Current machine learning systems are fundamentally deficient compared to animal and human learning because they lack techniques that enable machines to build background knowledge, common sense understanding of the physical world, and the capacity to reason and plan—capabilities that allow humans and animals to learn new tasks extremely quickly and understand how the world worksThe Shape of AI to Come! Yann LeCun at AI Action Summit 2025
- Current machine learning systems are fundamentally inadequate compared to human and animal learning because they lack the background knowledge, common sense, and causal understanding of the physical world that allows humans and animals to learn new tasks extremely quickly and reason about the world.The Shape of AI to Come! Yann LeCun at AI Action Summit 2025
- Large language models can generate fluent text by predicting probability distributions over words in sequence, but this capability masks fundamental stupidity because they lack understanding of the physical world, causal reasoning, and common sense that even animals like cats possess.AI: Grappling with a New Kind of Intelligence | World Science Festival
- Common sense has been a fundamental challenge in AI since the field's beginning, with people trying all kinds of approaches to give machines common sense, but machines 'severely lack it' currently.The Future of Artificial Intelligence
- Common sense, the ability to make reasonable inferences about likely outcomes without having to experience the mistake first, is now achievable via LLMs and VLMs (e.g. predicting that a slippery floor sign means caution), a capability that did not exist five years ago and is critical for safe robotic behavior.Fully autonomous robots are much closer than you think – Sergey Levine
- Hans Moravec proposed Moravec's Paradox in the 1980s: it is comparatively easy to make computers exhibit adult-level performance on intelligence tests or games like checkers and chess, but difficult or impossible to give them the skills of a one-year-old in perception and mobility, and Mitchell would add common sense to this observation.The Future of Artificial Intelligence
- Current deep learning systems make no attempt to construct knowledge representations or common sense; an image recognizer trained on millions of animal photos cannot answer which animals could pick up a suitcase, because it has learned statistical correlations rather than understanding—exemplified by a system that passed the University of Tokyo entrance exam while having no idea what any question means.94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans