DeepAI AI Chat
Log In Sign Up

Impossibility Results in AI: A Survey

by   Mario Brcic, et al.

An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the super-intelligent one. As such, these results serve as guidelines, reminders, and warnings to AI safety, AI policy, and governance researchers. These might enable solutions to some long-standing questions in the form of formalizing theories in the framework of constraint satisfaction without committing to one option. In this paper, we have categorized impossibility theorems applicable to the domain of AI into five categories: deduction, indistinguishability, induction, tradeoffs, and intractability. We found that certain theorems are too specific or have implicit assumptions that limit application. Also, we added a new result (theorem) about the unfairness of explainability, the first explainability-related result in the induction category. We concluded that deductive impossibilities deny 100 give some ideas that hold potential in explainability, controllability, value alignment, ethics, and group decision-making. They can be deepened by further investigation.


page 1

page 2

page 3

page 4


Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives

National and international guidelines for trustworthy artificial intelli...

Scope and Sense of Explainability for AI-Systems

Certain aspects of the explainability of AI systems will be critically d...

A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Act

This study discusses the interplay between metrics used to measure the e...

Grounding Explainability Within the Context of Global South in XAI

In this position paper, we propose building a broader and deeper underst...

On Avoiding Power-Seeking by Artificial Intelligence

We do not know how to align a very intelligent AI agent's behavior with ...

On the Weihrauch degree of the additive Ramsey theorem

We characterize the strength, in terms of Weihrauch degrees, of certain ...

Robust Computer Algebra, Theorem Proving, and Oracle AI

In the context of superintelligent AI systems, the term "oracle" has two...