• Corpus ID: 31495758

Detecting Qualia in Natural and Artificial Agents

@article{Yampolskiy2017DetectingQI,
  title={Detecting Qualia in Natural and Artificial Agents},
  author={Roman V Yampolskiy},
  journal={ArXiv},
  year={2017},
  volume={abs/1712.04020}
}
The Hard Problem of consciousness has been dismissed as an illusion. By showing that computers are capable of experiencing, we show that they are at least rudimentarily conscious with potential to eventually reach superconsciousness. The main contribution of the paper is a test for confirming certain subjective experiences in a tested agent. We follow with analysis of benefits and problems with conscious machines and implications of such capability on future of computing, machine rights and… 
View PDF on arXiv
14 Citations
Background Citations
7

Figures from this paper

14 Citations

Citation Type

Citation Type

Detecting Synthetic Phenomenology in a Contained Artificial General Intelligence
TLDR
This work provides an analysis of existing measures of phenomenology through qualia and extends those ideas into the context of a contained artificial general intelligence.
Preliminary Mediated Artificial Superintelligence Study, Experimental Framework, and Definitions for an Independent Core Observer Model Cognitive Architecture-Based System
TLDR
The initial proposal is that an mASI system based on the ICOM cognitive architecture for Artificial General Intelligence (AGI) may, as a whole, be conscious, self-aware, pass the Turing Test, suggest the presence of subjective phenomenology and/or satisfy other subjective measures of Artificial Super Intelligence (ASI), or intelligence well above the human standard.
An Objective Laboratory Protocol for Evaluating Cognition of Non-Human Systems Against Human Cognition
TLDR
This paper describes and reduces to practice an objective protocol for evaluating the cognitive capabilities of a non-human system against human cognition in a laboratory environment and provides insight into the areas where and to what extent a particular system falls short of human cognition.
Finite State Machines with Feedback: An Architecture Supporting Minimal Machine Consciousness
TLDR
The model is designed in the spirit of automata theory and presents a mix of Alan Turing's finite state machines and Norbert Wiener's machines with feedback, supporting the claim that consciousness is a computational phenomenon that is not just a matter of suitable software but also requires a dedicated architecture.
Quantum Metalanguage and The New Cognitive Synthesis
TLDR
A fundamentally new approach to problems of cognition that is based on completely innate behavioral programs is proposed, which involves the selection of adequate a priori existing (innate) programs that are most adequate to a given situation.
Preliminary Results and Analysis Independent Core Observer Model (ICOM) Cognitive Architecture in a Mediated Artificial Super Intelligence (mASI) System
TLDR
Some preliminary cognitive and consciousness test results of using an Independent Core Observer Model Cognitive Architecture (ICOM) in a Mediated Artificial Super Intelligence (mASI) System are focused on to determine whether this modified version of ICOM is a form of AGI and/or ASI, conscious and at least sufficiently interesting that further research is called for.
Extending Environments To Measure Self-Reflection In Reinforcement Learning
TLDR
It is argued that for an agent to achieve on-average good performance across many such extended environments, it is necessary for the agent to self-reflect, and an agent’s self-reflection ability can be numerically estimated by running the agent through a battery of extended environments.
Independent Core Observer Model (ICOM) Theory of Consciousness as Implemented in the ICOM Cognitive Architecture and the Associated Consciousness Measures
TLDR
The fundamental theory of consciousness used in the Independent Core Observer Model (ICOM) research program and the consciousness measures as applied to ICOM systems and their uses in context are articulated.
A Psychopathological Approach to Safety Engineering in AI and AGI
TLDR
This work proposes the modeling of deleterious behaviors in AI and AGI as psychological disorders, thereby enabling the employment of psychopathological approaches to analysis and control of misbehaviors.
Personal Universes: A Solution to the Multi-Agent Value Alignment Problem
TLDR
This paper assumes that the value extraction problem will be solved and proposes a possible way to implement an AI solution which optimally aligns with individual preferences of each user, and analyzed benefits and limitations of the proposed approach.
...
...

References

SHOWING 1-10 OF 223 REFERENCES
Phenomenal consciousness: the explanatory gap as a cognitive illusion
The thesis that there is a troublesome explanatory gap between the phenomenal aspects of experiences and the underlying physical and functional states is given a number of different interpretations.…
What is consciousness, and could machines have it?
TLDR
It is argued that despite their recent successes, current machines are still mostly implementing computations that reflect unconscious processing in the human brain, and the word “consciousness” conflates two different types of information-processing computations in the brain.
Could There be a Turing Test for Qualia
The paper examines the possibility of a Turing test designed to answer the question of whether a computational artefact is a genuine subject of conscious experience. Even given the severe…
Is Anyone Home? A Way to Find Out If AI Has Become Self-Aware
Recent articles by Schneider and Turner (Turner and Schneider, 2017; Schneider and Turner, 2017) outline an artificial consciousness test (ACT); a new, purely behavioural process to probe subjective…
Safety Engineering for Artificial General Intelligence
TLDR
It is argued that attempts to attribute moral agency and assign rights to all intelligent machines are misguided, whether applied to infrahuman or superhuman AIs, and a new science of safety engineering for intelligent artificial agents based on maximizing for what humans value is proposed.
SUPER-INTELLIGENCE AND (SUPER-)CONSCIOUSNESS
In this paper, the notion of super-intelligence (or "AI++", as Chalmers has termed it) is considered in the context of machine consciousness (MC) research. Suppose AI++ were to come about, would real…
Seeing Red: A Study in Consciousness
From sensations that probably began in bodily expression to the evolutionary advantages of a conscious self, 'Seeing Red' tracks the 'hard problem' of consciousness to its source and its solution, a…
Utility function security in artificially intelligent agents
TLDR
It is concluded that wireheading in rational self-improving optimisers above a certain capacity remains an unsolved problem despite opinion of many that such machines will choose not to wirehead.
On a confusion about a function of consciousness
  • N. Block
  • Psychology, Biology
    Behavioral and Brain Sciences
  • 1995
TLDR
This target article uses as an example a form of reasoning about a function of “consciousness” based on the phenomenon of blindsight, where an obvious function of the machinery of accessconsciousness is illicitly transferred to phenomenal consciousness.
Knowledge in perception and illusion.
  • R. Gregory
  • Psychology
    Philosophical transactions of the Royal Society of London. Series B, Biological sciences
  • 1997
TLDR
Visual illusions can provide evidence of object knowledge and working rules for vision, but only when the phenomena are explained and classified, which makes it hard to define 'illusion'.
...
...