Predictable Artificial Intelligence
We introduce the fundamental ideas and challenges of Predictable AI, a nascent research area that explores the ways in which we can anticipate key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. Predictable AI is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field.
Code (0)
등록된 구현이 없습니다.
Tasks
validSimilar Papers 제목 키워드 기반
Human-in-the-loop Artificial Intelligence
Little by little, newspapers are revealing the bright future that Artificial Intelligence (AI) is building. Intelligent machines will help everywhere. However, this bright future has a dark side: a dramatic job market co…
A Theory of Chaordic Economics: How Artificial Intelligence and Blockchain Transform Businesses, Economies and Societies
Dee Hock, the founder of Visa, coined the term 'chaordic' to describe simultaneously chaotic and ordered systems. Based on his reasoning, we introduce the Theory of Chaordic Economics to explain how economic systems are …
Analyzing Cyber-Physical Systems from the Perspective of Artificial Intelligence
Principles of modern cyber-physical system (CPS) analysis are based on analytical methods that depend on whether safety or liveness requirements are considered. Complexity is abstracted through different techniques, rang…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Digital Domination: A Case for Republican Liberty in Artificial Intelligence
Artificial intelligence is set to revolutionize social and political life in unpredictable ways, raising questions about the principles that ought to guide its development and regulation. By examining digital advertising…
FlyAI -- The Next Level of Artificial Intelligence is Unpredictable! Injecting Responses of a Living Fly into Decision Making
In this paper, we introduce a new type of bionic AI that enhances decision-making unpredictability by incorporating responses from a living fly. Traditional AI systems, while reliable and predictable, lack nuanced and so…
AI AgentDecision Making