paper-with-me

Papers

Building Safer AGI by introducing Artificial Stupidity

2018-08-11 · Michaël Trazzi, Roman V. Yampolskiy

Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the task. An Artificial General Intelligence (AGI) can be made safer by limiting its computing power and memory, or by introducing Artificial Stupidity on certain tasks. We survey human intellectual limits and give recommendations for which limits to implement in order to build a safe AGI.

📄 PDF Abstract BibTeX arXiv:1808.03644

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Artificial Stupidity

2020-07-02 · Michael Falk

Public debate about AI is dominated by Frankenstein Syndrome, the fear that AI will become superhuman and escape human control. Although superintelligence is certainly a possibility, the interest it excites can distract …

The Sixth Law of Stupidity: A Biophysical Interpretation of Carlo Cipolla's Stupidity Laws

2021-03-31 · Ilaria Perissi, Ugo Bardi

Carlo Cipolla's stupidity quadrant and his five laws of stupidity were proposed for the first time in 1976. Exposed in a humorous mood by the author, these concepts nevertheless describe very serious features of the inte…

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

2023-10-19 · Jiaming Ji, Borong Zhang, Jiayi Zhou, Xuehai Pan 외

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emer…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark

2023-09-26 · NeurIPS 2023 11

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emer…

The inherent goodness of well educated intelligence

2024-01-09 · Michael E. Glinsky

This paper will examine what makes a being intelligent, whether that be a biological being or an artificial silicon being on a computer. Special attention will be paid to the being having the ability to characterize and …