activity
20172022
most citedLow Impact Artificial Intelligences

15 citations · 26 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

5 papers · 1 filter

cs.AI20229 cited

Recognising the importance of preference change: A call for a coordinated multidisciplinary research effort in the age of AI

Matija Franklin, Hal Ashton, Rebecca Gorman +1

As artificial intelligence becomes more powerful and a ubiquitous presence in daily life, it is imperative to understand and manage the impact of AI systems on our lives and decisi…

cs.AI2022

The dangers in algorithms learning humans' values and irrationalities

Rebecca Gorman, Stuart Armstrong

For an artificial intelligence (AI) to be aligned with human values (or human preferences), it must first learn those values. AI systems that are trained on human behavior, risk mi…

cs.AI2020

Chess as a Testing Grounds for the Oracle Approach to AI Safety

James D. Miller, Roman Yampolskiy, Olle Haggstrom +1

To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages. This paper proposes a possibly practical m…

cs.AI20181 cited

Counterfactual equivalence for POMDPs, and underlying deterministic environments

Stuart Armstrong

Partially Observable Markov Decision Processes (POMDPs) are rich environments often used in machine learning. But the issue of information and causal structures in POMDPs has been…

cs.AI201715 cited

Low Impact Artificial Intelligences

Stuart Armstrong, Benjamin Levinstein

There are many goals for an AI that could become dangerous if the AI becomes superintelligent or otherwise powerful. Much work on the AI control problem has been focused on constru…