Understanding and Controlling Artificial General Intelligent Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F17%3A00474350" target="_blank" >RIV/67985807:_____/17:00474350 - isvavai.cz</a>

Výsledek na webu

<a href="http://aisb2017.cs.bath.ac.uk/proceedings.html" target="_blank" >http://aisb2017.cs.bath.ac.uk/proceedings.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Understanding and Controlling Artificial General Intelligent Systems

Popis výsledku v původním jazyce

Artificial general intelligence (AGI) systems are advancing in all parts of our society. The potential of autonomous systems that surpass the capabilities of human intelligence has stirred debates everywhere. How should ‘super-intelligent’ AGI systems be viewed so they can be feasibly controlled? We approach this question based on the viewpoints of the epistemic philosophy of computation, which treats AGI systems as computational systems processing knowledge over some domain. Rather than considering their autonomous development based on ‘self-improving software’, as is customary in the literature about super-intelligence, we consider AGI systems as operating with ‘self-improving epistemic theories’ that automatically increase their understanding of the world around them. We outline a number of algorithmic principles by which the self-improving theories can be constructed. Then we discuss the problem of aligning the behavior of AGI systems with human values in order to make such systems safe. This issue arises concretely when one studies the social and ethical aspects of human-robot interaction in advanced AGI systems as they exist already today. No general solution to this problem is known. However, based on the principles of interactive proof systems, we design an architecture of AGI systems and an interactive scenario that will enable one to detect in their behavior deviations from the prescribed goals. The conclusions from our analysis of AGI systems temper the over-optimistic expectations and over-pessimistic fears of singularity believers, by grounding the ideas on super-intelligent AGI systems in more realistic foundations.

Název v anglickém jazyce

Understanding and Controlling Artificial General Intelligent Systems

Popis výsledku anglicky

Artificial general intelligence (AGI) systems are advancing in all parts of our society. The potential of autonomous systems that surpass the capabilities of human intelligence has stirred debates everywhere. How should ‘super-intelligent’ AGI systems be viewed so they can be feasibly controlled? We approach this question based on the viewpoints of the epistemic philosophy of computation, which treats AGI systems as computational systems processing knowledge over some domain. Rather than considering their autonomous development based on ‘self-improving software’, as is customary in the literature about super-intelligence, we consider AGI systems as operating with ‘self-improving epistemic theories’ that automatically increase their understanding of the world around them. We outline a number of algorithmic principles by which the self-improving theories can be constructed. Then we discuss the problem of aligning the behavior of AGI systems with human values in order to make such systems safe. This issue arises concretely when one studies the social and ethical aspects of human-robot interaction in advanced AGI systems as they exist already today. No general solution to this problem is known. However, based on the principles of interactive proof systems, we design an architecture of AGI systems and an interactive scenario that will enable one to detect in their behavior deviations from the prescribed goals. The conclusions from our analysis of AGI systems temper the over-optimistic expectations and over-pessimistic fears of singularity believers, by grounding the ideas on super-intelligent AGI systems in more realistic foundations.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of AISB Annual Convention 2017

ISBN

978-1-908187-81-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

356-363

Název nakladatele

AISB

Místo vydání

London

Místo konání akce

Bath

Datum konání akce

18. 4. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—