View source for Artificial consciousness

{{Short description|Field in cognitive science}}{{Artificial intelligence}}

'''Artificial consciousness''',<ref>{{cite journal|last1 = Thaler|first1 = S. L.|year = 1998|title = The emerging intelligence and its critical look at us|journal = Journal of Near-Death Studies|volume = 17|issue = 1| pages = 21–29| doi = 10.1023/A:1022990118714|s2cid = 49573301}}</ref> also known as '''machine consciousness''',{{sfn|Gamez|2008}}{{sfn|Reggia|2013}} '''synthetic consciousness''',<ref>{{Cite journal|last1=Smith|first1=David Harris|last2=Schillaci|first2=Guido|date=2021|title=Build a Robot With Artificial Consciousness? How to Begin? A Cross-Disciplinary Dialogue on the Design and Implementation of a Synthetic Model of Consciousness|journal=Frontiers in Psychology|volume=12|page=530560|doi=10.3389/fpsyg.2021.530560|pmid=33967869|pmc=8096926|issn=1664-1078|doi-access=free}}</ref> or '''digital consciousness''',<ref>{{Cite book|last=Elvidge|first=Jim|url=https://books.google.com/books?id=kIqttQEACAAJ|title=Digital Consciousness: A Transformative Vision|date=2018|publisher=John Hunt Publishing Limited|isbn=978-1-78535-760-2|language=en|access-date=2023-06-28|archive-date=2023-07-30|archive-url=https://web.archive.org/web/20230730001838/https://books.google.com/books?id=kIqttQEACAAJ|url-status=live}}</ref> is the [[consciousness]] hypothesized to be possible in [[artificial intelligence]].<ref>{{cite journal|last1=Chrisley|first1=Ron|title=Philosophical foundations of artificial consciousness|journal=Artificial Intelligence in Medicine|date=October 2008|volume=44|issue=2|pages=119–137|doi=10.1016/j.artmed.2008.07.011|pmid=18818062|url=https://www.sciencedirect.com/science/article/abs/pii/S0933365708001000}}</ref> It is also the corresponding field of study, which draws insights from [[philosophy of mind]], [[philosophy of artificial intelligence]], [[cognitive science]] and [[neuroscience]].

The same terminology can be used with the term "[[sentience]]" instead of "consciousness" when specifically designating phenomenal consciousness (the ability to feel [[qualia]]).<ref>{{Cite web |last= |first= |title=The Terminology of Artificial Sentience |url=http://www.sentienceinstitute.org/blog/artificial-sentience-terminology |url-status=live |archive-url=https://web.archive.org/web/20240925040618/https://www.sentienceinstitute.org/blog/artificial-sentience-terminology |archive-date=2024-09-25 |access-date=2023-08-19 |website=Sentience Institute |language=en}}</ref> Since sentience involves the ability to experience ethically positive or negative (i.e., ''valenced'') mental states, it may justify welfare concerns and legal protection, as with animals.<ref name=":2" />

Some [[scholar]]s believe that consciousness is generated by the interoperation of various parts of the [[brain]]; these mechanisms are labeled the [[neural correlates of consciousness]] or NCC. Some further believe that constructing a [[system]] (e.g., a [[computer]] system) that can emulate this NCC interoperation would result in a system that is conscious.{{sfn|Graziano|2013}}

==Philosophical views==
As there are many hypothesized [[Consciousness#Types of consciousness|types of consciousness]], there are many potential implementations of artificial consciousness. In the philosophical literature, perhaps the most common taxonomy of consciousness is into "access" and "phenomenal" variants. Access consciousness concerns those aspects of [[experience]] that can be apprehended, while phenomenal consciousness concerns those aspects of experience that seemingly cannot be apprehended, instead being characterized qualitatively in terms of "raw feels", "what it is like" or qualia.<ref>{{Cite journal|last=Block|first=Ned|date=2010|title=On a confusion about a function of consciousness|url=https://www.cambridge.org/core/journals/behavioral-and-brain-sciences/article/abs/on-a-confusion-about-a-function-of-consciousness/061422BF0C50C5FF00927F9B6E879413|journal=Behavioral and Brain Sciences|language=en|volume=18|issue=2|pages=227–247|doi=10.1017/S0140525X00038188|s2cid=146168066|issn=1469-1825|access-date=2023-06-22|archive-date=2024-09-25|archive-url=https://web.archive.org/web/20240925040612/https://www.cambridge.org/core/journals/behavioral-and-brain-sciences/article/abs/on-a-confusion-about-a-function-of-consciousness/061422BF0C50C5FF00927F9B6E879413|url-status=live}}</ref>

=== Plausibility debate ===
[[Type physicalism|Type-identity theorists]] and other skeptics hold the view that consciousness can be realized only in particular physical systems because consciousness has properties that necessarily depend on physical constitution.<ref>{{Cite journal|last=Block|first=Ned|date=1978|title=Troubles for Functionalism|journal=Minnesota Studies in the Philosophy of Science|pages=261–325}}</ref><ref>{{Cite book|last=Bickle|first=John|url=http://link.springer.com/10.1007/978-94-010-0237-0|title=Philosophy and Neuroscience|date=2003|publisher=Springer Netherlands|isbn=978-1-4020-1302-7|location=Dordrecht|language=en|doi=10.1007/978-94-010-0237-0|access-date=2023-06-24|archive-date=2024-09-25|archive-url=https://web.archive.org/web/20240925040620/https://link.springer.com/book/10.1007/978-94-010-0237-0|url-status=live}}</ref><ref>{{cite journal|last1 = Schlagel|first1 = R. H.|year = 1999|title = Why not artificial consciousness or thought?|journal = Minds and Machines|volume = 9|issue = 1| pages = 3–28|doi=10.1023/a:1008374714117| s2cid = 28845966}}</ref><ref>{{cite journal|last1 = Searle|first1 = J. R.|year = 1980|title = Minds, brains, and programs|url = http://cogprints.org/7150/1/10.1.1.83.5248.pdf|journal = Behavioral and Brain Sciences|volume = 3|issue = 3|pages = 417–457|doi = 10.1017/s0140525x00005756|s2cid = 55303721|access-date = 2019-01-28|archive-date = 2019-03-17|archive-url = https://web.archive.org/web/20190317230215/http://cogprints.org/7150/1/10.1.1.83.5248.pdf|url-status = live}}</ref> In his 2001 article "Artificial Consciousness: Utopia or Real Possibility," [[Giorgio Buttazzo]] says that a common objection to artificial consciousness is that, "Working in a fully automated mode, they [the computers] cannot exhibit creativity, unreprogrammation (which means can 'no longer be reprogrammed', from rethinking), emotions, or [[free will]]. A computer, like a washing machine, is a slave operated by its components."<ref>{{Cite journal|last=Buttazzo|first=G.|date=2001|title=Artificial consciousness: Utopia or real possibility?|url=https://ieeexplore.ieee.org/document/933500|journal=Computer|volume=34|issue=7|pages=24–30|doi=10.1109/2.933500|access-date=2024-07-31|archive-date=2024-09-25|archive-url=https://web.archive.org/web/20240925040556/https://ieeexplore.ieee.org/document/933500/|url-status=live}}</ref>

For other theorists (e.g., [[Functionalism (philosophy of mind)|functionalists]]), who define mental states in terms of causal roles, any system that can instantiate the same pattern of causal roles, regardless of physical constitution, will instantiate the same mental states, including consciousness.<ref>{{Cite book|last=Putnam|first=Hilary|title=The nature of mental states in Capitan and Merrill (eds.) Art, Mind and Religion|publisher=University of Pittsburgh Press|year=1967}}</ref>

==== Thought experiments ====
[[David Chalmers]] proposed two [[thought experiments]] intending to demonstrate that "functionally [[isomorphic]]" systems (those with the same "fine-grained functional organization", i.e., the same information processing) will have qualitatively identical conscious experiences, regardless of whether they are based on biological neurons or digital hardware.<ref name=":6">{{Cite journal |last=Chalmers |first=David |date=1995 |title=Absent Qualia, Fading Qualia, Dancing Qualia |url=https://consc.net/papers/qualia.html |journal=Conscious Experience}}</ref><ref>{{Cite journal |last=David J. Chalmers |date=2011 |title=A Computational Foundation for the Study of Cognition |url=https://www.ida.liu.se/divisions/hcs/seminars/cogsciseminars/Papers/Chalmers_Computational_foundations.pdf |url-status=live |journal=Journal of Cognitive Science |volume=12 |issue=4 |pages=325–359 |doi=10.17791/JCS.2011.12.4.325 |s2cid=248401010 |archive-url=https://web.archive.org/web/20231123085948/https://www.ida.liu.se/divisions/hcs/seminars/cogsciseminars/Papers/Chalmers_Computational_foundations.pdf |archive-date=2023-11-23 |access-date=2023-06-24}}</ref>

The "fading qualia" is a ''[[reductio ad absurdum]]'' thought experiment. It involves replacing, one by one, the neurons of a brain with a functionally identical component, for example based on a [[Silicon chips|silicon chip]]. Since the original neurons and their silicon counterparts are functionally identical, the brain’s information processing should remain unchanged, and the subject would not notice any difference. However, if qualia (such as the subjective experience of bright red) were to fade or disappear, the subject would likely notice this change, which causes a contradiction. Chalmers concludes that the fading qualia hypothesis is impossible in practice, and that the resulting robotic brain, once every neurons are replaced, would remain just as sentient as the original biological brain.<ref name=":6" /><ref name=":7">{{Cite web |date=2023-09-30 |title=An Introduction to the Problems of AI Consciousness |url=https://thegradient.pub/an-introduction-to-the-problems-of-ai-consciousness/ |access-date=2024-10-05 |website=The Gradient |language=en}}</ref>

Similarly, the "dancing qualia" thought experiment is another ''reductio ad absurdum'' argument. It supposes that two functionally isomorphic systems could have different perceptions (for instance, seeing the same object in different colors, like red and blue). It involves a switch that alternates between a chunk of brain that causes the perception of red, and a functionally isomorphic silicon chip, that causes the perception of blue. Since both perform the same function within the brain, the subject would not notice any change during the switch. Chalmers argues that this would be highly implausible if the qualia were truly switching between red and blue, hence the contradiction. Therefore, he concludes that the equivalent digital system would not only experience qualia, but it would perceive the same qualia as the biological system (e.g., seeing the same color).<ref name=":6" /><ref name=":7" />

Critics{{who|date=May 2023}} of artificial sentience object that Chalmers' proposal begs the question in assuming that all mental properties and external connections are already sufficiently captured by abstract causal organization.
==== In large language models ====
In 2022, Google engineer Blake Lemoine made a viral claim that Google's [[LaMDA]] chatbot was sentient. Lemoine supplied as evidence the chatbot's humanlike answers to many of his questions; however, the chatbot's behavior was judged by the scientific community as likely a consequence of mimicry, rather than machine sentience. Lemoine's claim was widely derided for being ridiculous.<ref>{{cite news|date=14 August 2022|title='I am, in fact, a person': can artificial intelligence ever be sentient?|language=en|work=the Guardian|url=https://www.theguardian.com/technology/2022/aug/14/can-artificial-intelligence-ever-be-sentient-googles-new-ai-program-is-raising-questions|access-date=5 January 2023|archive-date=25 September 2024|archive-url=https://web.archive.org/web/20240925040732/https://www.theguardian.com/technology/2022/aug/14/can-artificial-intelligence-ever-be-sentient-googles-new-ai-program-is-raising-questions|url-status=live}}</ref> However, while philosopher [[Nick Bostrom]] states that LaMDA is unlikely to be conscious, he additionally poses the question of "what grounds would a person have for being sure about it?" One would have to have access to unpublished information about LaMDA's architecture, and also would have to understand how consciousness works, and then figure out how to map the philosophy onto the machine: "(In the absence of these steps), it seems like one should be maybe a little bit uncertain.{{nbsp}}[...] there could well be other systems now, or in the relatively near future, that would start to satisfy the criteria."<ref>{{cite news|last1=Leith|first1=Sam|date=7 July 2022|title=Nick Bostrom: How can we be certain a machine isn't conscious?|work=The Spectator|url=https://www.spectator.co.uk/article/nick-bostrom-how-can-we-be-certain-a-machine-isnt-conscious/|access-date=5 January 2023|archive-date=5 January 2023|archive-url=https://web.archive.org/web/20230105074430/https://www.spectator.co.uk/article/nick-bostrom-how-can-we-be-certain-a-machine-isnt-conscious/|url-status=live}}</ref>

Kristina Šekrst argues that, related to [[Large language model|large language models]] (LLMs), it is fundamentally impossible to distinguish between genuine artificial consciousness and a form of [[AI hallucination]], since both can result in outputs that appear human-like without any underlying subjective experience. Furthermore, Šekrst contends that training LLMs on data that omits references to [[qualia]] - the essential, subjective aspects of experience - prevents these systems from ever attaining true understanding, confining them instead to sophisticated pattern recognition.<ref name="Šekrst">{{Citation|last=Šekrst |first=Kristina |year=2025 |title=Do Large Language Models Hallucinate Electric Fata Morganas? |journal=Journal of Consciousness Studies|url=https://philpapers.org/rec/EKRDLL}}</ref>

[[David Chalmers]] argued in 2023 that LLMs today display impressive conversational and general intelligence abilities, but are likely not conscious yet, as they lack some features that may be necessary, such as recurrent processing, a [[Global workspace theory|global workspace]], and unified agency. Nonetheless, he considers that non-biological systems can be conscious, and suggested that future, extended models (LLM+s) incorporating these elements might eventually meet the criteria for consciousness, raising both profound scientific questions and significant ethical challenges.<ref name=":3" />

=== Testing ===
Qualia, or phenomenological consciousness, is an inherently first-person phenomenon. Because of that, and the lack of an empirical definition of sentience, directly measuring it may be impossible. Although systems may display numerous behaviors correlated with sentience, determining whether a system is sentient is known as the [[hard problem of consciousness]]. In the case of AI, there is the additional difficulty that the AI may be trained to act like a human, or incentivized to appear sentient, which makes behavioral markers of sentience less reliable.<ref>{{Cite news |last=Véliz |first=Carissa |date=2016-04-14 |title=The Challenge of Determining Whether an A.I. Is Sentient |url=https://slate.com/technology/2016/04/the-challenge-of-determining-whether-an-a-i-is-sentient.html |access-date=2024-10-05 |work=Slate |language=en-US |issn=1091-2339}}</ref><ref>{{Cite book |last=Birch |first=Jonathan |url=https://academic.oup.com/book/57949/chapter/475705460 |title=The Edge of Sentience |date=July 2024 |publisher=Oxford University Press |chapter=Large Language Models and the Gaming Problem|pages=313–322 |doi=10.1093/9780191966729.003.0017 |isbn=978-0-19-196672-9 }}</ref> Additionally, some chatbots have been trained to say they are not conscious.<ref>{{Cite news |last1=Agüera y Arcas |first1=Blaise |last2=Norvig |first2=Peter |date=October 10, 2023 |title=Artificial General Intelligence Is Already Here |url=https://www.noemamag.com/artificial-general-intelligence-is-already-here/ |work=Noéma}}</ref>

A well-known method for testing machine [[Intelligence (trait)|intelligence]] is the [[Turing test]], which assesses the ability to have a human-like conversation. But passing the Turing test does not indicate that an AI system is sentient, as the AI may simply mimic human behavior without having the associated feelings.<ref>{{Cite web |last1=Kirk-Giannini |first1=Cameron Domenico |last2=Goldstein |first2=Simon |date=2023-10-16 |title=AI is closer than ever to passing the Turing test for 'intelligence'. What happens when it does? |url=https://theconversation.com/ai-is-closer-than-ever-to-passing-the-turing-test-for-intelligence-what-happens-when-it-does-214721 |access-date=2024-08-18 |website=The Conversation |language=en-US |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925040612/https://theconversation.com/ai-is-closer-than-ever-to-passing-the-turing-test-for-intelligence-what-happens-when-it-does-214721 |url-status=live }}</ref>

In 2014, Victor Argonov suggested a non-Turing test for machine sentience based on machine's ability to produce philosophical judgments.<ref>{{cite journal|author=Victor Argonov|year=2014|title=Experimental Methods for Unraveling the Mind-body Problem: The Phenomenal Judgment Approach|url=http://philpapers.org/rec/ARGMAA-2|journal=Journal of Mind and Behavior|volume=35|pages=51–70|access-date=2016-12-06|archive-date=2016-10-20|archive-url=https://web.archive.org/web/20161020014221/http://philpapers.org/rec/ARGMAA-2|url-status=live}}</ref> He argues that a deterministic machine must be regarded as conscious if it is able to produce judgments on all problematic properties of consciousness (such as qualia or [[Binding problem|binding]]) having no innate (preloaded) philosophical knowledge on these issues, no philosophical discussions while learning, and no informational models of other creatures in its memory (such models may implicitly or explicitly contain knowledge about these creatures' consciousness). However, this test can be used only to detect, but not refute the existence of consciousness. A positive result proves that machine is conscious but a negative result proves nothing. For example, absence of philosophical judgments may be caused by lack of the machine's intellect, not by absence of consciousness.

=== Ethics ===
{{Main|Ethics of artificial intelligence|Machine ethics|Roboethics}}

If it were suspected that a particular machine was conscious, its rights would be an [[ethics|ethical]] issue that would need to be assessed (e.g. what rights it would have under law).<ref>{{Cite news |date=April 10, 2023 |title=Should Robots With Artificial Intelligence Have Moral or Legal Rights? |url=https://www.wsj.com/articles/robots-ai-legal-rights-3c47ef40 |work=The Wall Street Journal}}</ref> For example, a conscious computer that was owned and used as a tool or central computer within a larger machine is a particular ambiguity. Should [[law]]s be made for such a case? Consciousness would also require a legal definition in this particular case. Because artificial consciousness is still largely a theoretical subject, such ethics have not been discussed or developed to a great extent, though it has often been a theme in fiction.

Sentience is generally considered sufficient for moral consideration, but some philosophers consider that moral consideration could also stem from other notions of consciousness, or from capabilities unrelated to consciousness,<ref name=":4">{{Cite book |last=Bostrom |first=Nick |title=Deep utopia: life and meaning in a solved world |date=2024 |publisher=Ideapress Publishing |isbn=978-1-64687-164-3 |location=Washington, DC |page=82}}</ref><ref name=":5">{{Cite journal |last1=Sebo |first1=Jeff |last2=Long |first2=Robert |date=11 December 2023 |title=Moral Consideration for AI Systems by 2030 |url=https://jeffsebo.net/wp-content/uploads/2023/06/moral-consideration-for-ai-systems-by-2030-5.pdf |journal=AI and Ethics|doi=10.1007/s43681-023-00379-1 }}</ref> such as: "having a sophisticated conception of oneself as persisting through time; having agency and the ability to pursue long-term plans; being able to communicate and respond to normative reasons; having preferences and powers; standing in certain social relationships with other beings that have moral status; being able to make commitments and to enter into reciprocal arrangements; or having the potential to develop some of these attributes."<ref name=":4" />

Ethical concerns still apply (although to a lesser extent) [[Ethics of uncertain sentience|when the consciousness is uncertain]], as long as the probability is deemed non-negligible. The [[precautionary principle]] is also relevant if the moral cost of mistakenly attributing or denying moral consideration to AI differs significantly.<ref name=":5" /><ref name=":2" />

In 2021, German philosopher [[Thomas Metzinger]] argued for a global moratorium on synthetic phenomenology until 2050. Metzinger asserts that humans have a duty of care towards any sentient AIs they create, and that proceeding too fast risks creating an "explosion of artificial suffering".<ref>{{cite journal|doi=10.1142/S270507852150003X|title=Artificial Suffering: An Argument for a Global Moratorium on Synthetic Phenomenology|year=2021|last1=Metzinger|first1=Thomas|journal=Journal of Artificial Intelligence and Consciousness|volume=08|pages=43–66|s2cid=233176465|doi-access=free}}</ref> David Chalmers also argued that creating conscious AI would "raise a new group of difficult ethical challenges, with the potential for new forms of injustice".<ref name=":3" />

Enforced amnesia has been proposed as a way to mitigate the risk of [[silent suffering]] in locked-in conscious AI and certain AI-adjacent biological systems like [[organoid intelligence|brain organoids]].<ref name="aiamnesia">{{Cite journal |last1=Tkachenko |first1=Yegor |year=2024 |title=Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI |journal=Proceedings of the 41st International Conference on Machine Learning |url=https://openreview.net/forum?id=nACGn4US1R|access-date=2024-06-11 |publisher=PMLR |language=en |archive-date=2024-06-10 |archive-url=https://web.archive.org/web/20240610171754/https://openreview.net/forum?id=nACGn4US1R |url-status=live}}</ref>

== Aspects of consciousness ==
[[Bernard Baars]] and others argue there are various aspects of consciousness necessary for a machine to be artificially conscious.{{sfn|Baars|1995}} The functions of consciousness suggested by Baars are: definition and context setting, adaptation and learning, editing, flagging and debugging, recruiting and control, prioritizing and access-control, decision-making or executive function, analogy-forming function, metacognitive and self-monitoring function, and autoprogramming and self-maintenance function. [[Igor Aleksander]] suggested 12 principles for artificial consciousness:<ref>{{Cite book |last=Aleksander |first=Igor |title=From Natural to Artificial Neural Computation |chapter=Artificial neuroconsciousness an update |date=1995a |editor-last=Mira |editor-first=José |editor2-last=Sandoval |editor2-first=Francisco |chapter-url=https://link.springer.com/chapter/10.1007/3-540-59497-3_224 |series=Lecture Notes in Computer Science |volume=930 |language=en |location=Berlin, Heidelberg |publisher=Springer |pages=566–583 |doi=10.1007/3-540-59497-3_224 |isbn=978-3-540-49288-7 |access-date=2023-06-22 |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925040733/https://link.springer.com/chapter/10.1007/3-540-59497-3_224 |url-status=live}}</ref> the brain is a state machine, inner neuron partitioning, conscious and unconscious states, perceptual learning and memory, prediction, the awareness of self, representation of meaning, learning utterances, learning language, will, instinct, and emotion. The aim of AC is to define whether and how these and other aspects of consciousness can be synthesized in an engineered artifact such as a digital computer. This list is not exhaustive; there are many others not covered. 

=== Subjective experience ===
Some philosophers, such as [[David Chalmers]], use the term consciousness to refer exclusively to phenomenal consciousness, which is roughly equivalent to sentience. Others use the word sentience to refer exclusively to ''valenced'' (ethically positive or negative) subjective experiences, like pleasure or suffering.<ref name=":3">{{Cite news |last=Chalmers |first=David J. |date=August 9, 2023 |title=Could a Large Language Model Be Conscious? |url=https://www.bostonreview.net/articles/could-a-large-language-model-be-conscious/ |work=Boston Review}}</ref> Explaining why and how subjective experience arises is known as the [[hard problem of consciousness]].<ref>{{Cite web |last=Seth |first=Anil |title=Consciousness |url=https://www.newscientist.com/definition/consciousness/ |access-date=2024-09-05 |website=New Scientist |language=en-US |archive-date=2024-09-14 |archive-url=https://web.archive.org/web/20240914003058/https://www.newscientist.com/definition/consciousness/ |url-status=live }}</ref> AI sentience would give rise to concerns of welfare and legal protection,<ref name=":2">{{Cite magazine |last=Kateman |first=Brian |date=2023-07-24 |title=AI Should Be Terrified of Humans |url=https://time.com/6296234/ai-should-be-terrified-of-humans/ |access-date=2024-09-05 |magazine=TIME |language=en |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925041601/https://time.com/6296234/ai-should-be-terrified-of-humans/ |url-status=live }}</ref> whereas other aspects of consciousness related to cognitive capabilities may be more relevant for AI rights.<ref>{{Cite web |last=Nosta |first=John |date=December 18, 2023 |title=Should Artificial Intelligence Have Rights? |url=https://www.psychologytoday.com/us/blog/the-digital-self/202312/should-artificial-intelligence-have-rights |access-date=2024-09-05 |website=Psychology Today |language=en-US |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925041049/https://www.psychologytoday.com/us/blog/the-digital-self/202312/should-artificial-intelligence-have-rights |url-status=live }}</ref>

=== Awareness ===
[[Awareness]] could be one required aspect, but there are many problems with the exact definition of ''awareness''. The results of the experiments of [[Mirror neurons#In monkeys|neuroscanning on monkeys]] suggest that a process, not only a state or object, activates neurons. Awareness includes creating and testing alternative models of each process based on the information received through the senses or imagined,{{clarify|date=June 2023}} and is also useful for making predictions. Such modeling needs a lot of flexibility. Creating such a model includes modeling the physical world, modeling one's own internal states and processes, and modeling other conscious entities.

There are at least three types of awareness:<ref>Joëlle Proust in ''Neural Correlates of Consciousness'', Thomas Metzinger, 2000, MIT, pages 307–324</ref> agency awareness, goal awareness, and sensorimotor awareness, which may also be conscious or not. For example, in agency awareness, you may be aware that you performed a certain action yesterday, but are not now conscious of it. In goal awareness, you may be aware that you must search for a lost object, but are not now conscious of it. In sensorimotor awareness, you may be aware that your hand is resting on an object, but are not now conscious of it.

Because objects of awareness are often conscious, the distinction between awareness and consciousness is frequently blurred or they are used as synonyms.<ref>Christof Koch, ''The Quest for Consciousness'', 2004, page 2 footnote 2</ref>

=== Memory ===
Conscious events interact with [[memory]] systems in learning, rehearsal, and retrieval.<ref>Tulving, E. 1985. Memory and consciousness. Canadian Psychology 26:1–12</ref>
The [[#Intelligent Distribution Agent|IDA model]]<ref>Franklin, Stan, et al. "The role of consciousness in memory." Brains, Minds and Media 1.1 (2005): 38.</ref> elucidates the role of consciousness in the updating of perceptual memory,<ref>Franklin, Stan. "Perceptual memory and learning: Recognizing, categorizing, and relating." Proc. Developmental Robotics AAAI Spring Symp. 2005.</ref> transient [[episodic memory]], and [[procedural memory]]. Transient episodic and declarative memories have distributed representations in IDA; there is evidence that this is also the case in the nervous system.<ref>Shastri, L. 2002. Episodic memory and cortico-hippocampal interactions. Trends in Cognitive Sciences</ref> In IDA, these two memories are implemented computationally using a modified version of [[Pentti Kanerva|Kanerva]]’s [[sparse distributed memory]] architecture.<ref>Kanerva, Pentti. Sparse distributed memory. MIT press, 1988.</ref>

=== Learning ===
Learning is also considered necessary for artificial consciousness. Per Bernard Baars, conscious experience is needed to represent and adapt to novel and significant events.{{sfn|Baars|1995}} Per [[Axel Cleeremans]] and Luis Jiménez, learning is defined as "a set of philogenetically{{sic}} advanced adaptation processes that critically depend on an evolved sensitivity to subjective experience so as to enable agents to afford flexible control over their actions in complex, unpredictable environments".<ref>{{Cite web|title=Implicit Learning and Consciousness: An Empirical, Philosophical and Computational Consensus in the Making|url=https://www.routledge.com/Implicit-Learning-and-Consciousness-An-Empirical-Philosophical-and-Computational/Cleeremans-French/p/book/9781138877412|access-date=2023-06-22|website=Routledge & CRC Press|language=en|archive-date=2023-06-22|archive-url=https://web.archive.org/web/20230622223246/https://www.routledge.com/Implicit-Learning-and-Consciousness-An-Empirical-Philosophical-and-Computational/Cleeremans-French/p/book/9781138877412|url-status=live}}</ref>

=== Anticipation ===
The ability to predict (or [[Anticipation (artificial intelligence)|anticipate]]) foreseeable events is considered important for artificial intelligence by [[Igor Aleksander]].{{sfn|Aleksander|1995}} The emergentist [[Multiple Drafts Model|multiple drafts principle]] proposed by [[Daniel Dennett]] in ''[[Consciousness Explained]]'' may be useful for prediction: it involves the evaluation and selection of the most appropriate "draft" to fit the current environment. Anticipation includes prediction of consequences of one's own proposed actions and prediction of consequences of probable actions by other entities.

Relationships between real world states are mirrored in the state structure of a conscious organism, enabling the organism to predict events.{{sfn|Aleksander|1995}} An artificially conscious machine should be able to anticipate events correctly in order to be ready to respond to them when they occur or to take preemptive action to avert anticipated events. The implication here is that the machine needs flexible, real-time components that build spatial, dynamic, statistical, functional, and cause-effect models of the real world and predicted worlds, making it possible to demonstrate that it possesses artificial consciousness in the present and future and not only in the past. In order to do this, a conscious machine should make coherent predictions and contingency plans, not only in worlds with fixed rules like a chess board, but also for novel environments that may change, to be executed only when appropriate to simulate and control the real world.

== Functionalist theories of consciousness ==
[[Functionalism (philosophy of mind)|Functionalism]] is a theory that defines mental states by their functional roles (their causal relationships to sensory inputs, other mental states, and behavioral outputs), rather than by their physical composition. According to this view, what makes something a particular mental state, such as pain or belief, is not the material it is made of, but the role it plays within the overall cognitive system. It allows for the possibility that mental states, including consciousness, could be realized on non-biological substrates, as long as it instantiates the right functional relationships.<ref>{{Cite web |title=Functionalism |url=https://plato.stanford.edu/entries/functionalism/ |website=Stanford Encyclopedia of Philosophy |access-date=2024-09-08 |archive-date=2021-04-18 |archive-url=https://web.archive.org/web/20210418140903/http://plato.stanford.edu/entries/functionalism/ |url-status=live }}</ref> Functionalism is particularly popular among philosophers.<ref>{{Cite web |date=2020 |title=Survey Results {{!}} Consciousness: identity theory, panpsychism, eliminativism, dualism, or functionalism? |url=https://survey2020.philpeople.org/survey/results/5010 |website=PhilPapers}}</ref>

A 2023 study suggested that current [[Large language model|large language models]] probably don't satisfy the criteria for consciousness suggested by these theories, but that relatively simple AI systems that satisfy these theories could be created. The study also acknowledged that even the most prominent theories of consciousness remain incomplete and subject to ongoing debate.<ref>{{Cite arXiv |date=2023 |title=Consciousness in Artificial Intelligence: Insights from the Science of Consciousness |eprint=2308.08708 |last1=Butlin |first1=Patrick |last2=Long |first2=Robert |last3=Elmoznino |first3=Eric |last4=Bengio |first4=Yoshua |last5=Birch |first5=Jonathan |last6=Constant |first6=Axel |last7=Deane |first7=George |last8=Fleming |first8=Stephen M. |last9=Frith |first9=Chris |last10=Ji |first10=Xu |last11=Kanai |first11=Ryota |last12=Klein |first12=Colin |last13=Lindsay |first13=Grace |last14=Michel |first14=Matthias |last15=Mudrik |first15=Liad |last16=Peters |first16=Megan A. K. |last17=Schwitzgebel |first17=Eric |last18=Simon |first18=Jonathan |last19=VanRullen |first19=Rufin |class=cs.AI }}</ref>

=== Global workspace theory ===
{{Main|Global workspace theory}}
This theory analogizes the mind to a theater, with conscious thought being like material illuminated on the main stage. The brain contains many specialized processes or modules (such as those for vision, language, or memory) that operate in parallel, much of which is unconscious. Attention acts as a spotlight, bringing some of this unconscious activity into conscious awareness on the global workspace. The global workspace functions as a hub for broadcasting and integrating information, allowing it to be shared and processed across different specialized modules. For example, when reading a word, the visual module recognizes the letters, the language module interprets the meaning, and the memory module might recall associated information – all coordinated through the global workspace.<ref>{{cite book |last1=Baars |first1=Bernard J. |url=http://cogweb.ucla.edu/Abstracts/Baars_88.html |title=A Cognitive Theory of Consciousness |date=1988 |publisher=Cambridge University Press |isbn=0521427436 |page=345 |access-date=2024-09-05 |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925041604/http://cogweb.ucla.edu/Abstracts/Baars_88.html |url-status=live }}</ref><ref name=":1">{{Cite web |last=Travers |first=Mark |date=October 11, 2023 |title=Are We Ditching the Most Popular Theory of Consciousness? |url=https://www.psychologytoday.com/us/blog/social-instincts/202310/are-we-ditching-the-most-popular-theory-of-consciousness |access-date=2024-09-05 |website=Psychology Today |language=en-US |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925041550/https://www.psychologytoday.com/us/blog/social-instincts/202310/are-we-ditching-the-most-popular-theory-of-consciousness |url-status=live }}</ref>

=== Higher-order theories of consciousness ===
{{Main|Higher-order theories of consciousness}}
Higher-order theories of consciousness propose that a mental state becomes conscious when it is the object of a higher-order representation, such as a thought or perception about that state. These theories argue that consciousness arises from a relationship between lower-order mental states and higher-order awareness of those states. There are several variations, including higher-order thought (HOT) and higher-order perception (HOP) theories.<ref name="Carruthers2011">{{cite web |author1= |date=15 Aug 2011 |title=Higher-Order Theories of Consciousness |url=http://plato.stanford.edu/entries/consciousness-higher/ |access-date=31 August 2014 |website=Stanford Encyclopedia of Philosophy |archive-date=14 May 2008 |archive-url=https://web.archive.org/web/20080514053751/http://plato.stanford.edu/entries/consciousness-higher/ |url-status=live }}</ref><ref name=":1" />

=== Attention schema theory ===
{{Main|Attention schema theory}}
In 2011, [[Michael Graziano]] and Sabine Kastler published a paper named "Human consciousness and its relationship to social neuroscience: A novel hypothesis" proposing a theory of consciousness as an attention schema.<ref>{{cite journal |last1=Graziano |first1=Michael |date=1 January 2011 |title=Human consciousness and its relationship to social neuroscience: A novel hypothesis |journal=Cognitive Neuroscience |volume=2 |issue=2 |pages=98–113 |doi=10.1080/17588928.2011.565121 |pmc=3223025 |pmid=22121395}}</ref> Graziano went on to publish an expanded discussion of this theory in his book "Consciousness and the Social Brain".{{sfn|Graziano|2013}} This Attention Schema Theory of Consciousness, as he named it, proposes that the brain tracks attention to various sensory inputs by way of an attention schema, analogous to the well-studied body schema that tracks the spatial place of a person's body.{{sfn|Graziano|2013}} This relates to artificial consciousness by proposing a specific mechanism of information handling, that produces what we allegedly experience and describe as consciousness, and which should be able to be duplicated by a machine using current technology. When the brain finds that person X is aware of thing Y, it is in effect modeling the state in which person X is applying an attentional enhancement to Y. In the attention schema theory, the same process can be applied to oneself. The brain tracks attention to various sensory inputs, and one's own awareness is a schematized model of one's attention. Graziano proposes specific locations in the brain for this process, and suggests that such awareness is a computed feature constructed by an expert system in the brain.

==Implementation proposals==
{{See also|Cognitive architecture}}
===Symbolic or hybrid===
====Learning Intelligent Distribution Agent====
{{main|LIDA (cognitive architecture)}}

[[Stan Franklin]] created a cognitive architecture called [[LIDA (cognitive architecture)|LIDA]] that implements [[Bernard Baars]]'s theory of consciousness called the [[global workspace theory]]. It relies heavily on ''codelets'', which are "special purpose, relatively independent, mini-agent[s] typically implemented as a small piece of code running as a separate thread." Each element of cognition, called a "cognitive cycle" is subdivided into three phases: understanding, consciousness, and action selection (which includes learning). LIDA reflects the global workspace theory's core idea that consciousness acts as a workspace for integrating and broadcasting the most important information, in order to coordinate various cognitive processes.<ref>{{Cite journal |last=Franklin |first=Stan |date=January 2003 |title=IDA: A conscious artifact? |url=https://www.researchgate.net/publication/233597270 |journal=Journal of Consciousness Studies |access-date=2024-08-25 |archive-date=2020-07-03 |archive-url=https://web.archive.org/web/20200703105206/https://www.researchgate.net/publication/233597270_IDA_A_conscious_artifact |url-status=live }}</ref><ref name=":02">{{Cite journal |last1=J. Baars |first1=Bernard |last2=Franklin |first2=Stan |date=2009 |title=Consciousness is computational: The Lida model of global workspace theory |url=https://philpapers.org/rec/BERCIC |journal=International Journal of Machine Consciousness|volume=01 |pages=23–32 |doi=10.1142/S1793843009000050 }}</ref>

====CLARION cognitive architecture====
{{main|CLARION (cognitive architecture)}}
The CLARION cognitive architecture models the mind using a two-level system to distinguish between conscious ("explicit") and unconscious ("implicit") processes. It can simulate various learning tasks, from simple to complex, which helps researchers study in psychological experiments how consciousness might work.<ref>{{Harv|Sun|2002}}</ref>

====OpenCog====
[[Ben Goertzel]] made an embodied AI through the open-source [[OpenCog]] project. The code includes embodied virtual pets capable of learning simple English-language commands, as well as integration with real-world robotics, done at the [[Hong Kong Polytechnic University]].

===Connectionist===
====Haikonen's cognitive architecture====
Pentti Haikonen considers classical rule-based computing inadequate for achieving AC: "the brain is definitely not a computer. Thinking is not an execution of programmed strings of commands. The brain is not a numerical calculator either. We do not think by numbers." Rather than trying to achieve [[mind]] and consciousness by identifying and implementing their underlying computational rules, Haikonen proposes "a special [[cognitive architecture]] to reproduce the processes of [[perception]], [[Mental image|inner imagery]], [[Intrapersonal communication|inner speech]], [[pain]], [[pleasure]], [[emotions]] and the [[cognitive]] functions behind these. This bottom-up architecture would produce higher-level functions by the power of the elementary processing units, the [[artificial neuron]]s, without [[algorithms]] or [[computer program|programs]]". Haikonen believes that, when implemented with sufficient complexity, this architecture will develop consciousness, which he considers to be "a style and way of operation, characterized by distributed signal representation, perception process, cross-modality reporting and availability for retrospection."<ref>{{Cite book |last=Haikonen |first=Pentti O. |title=The cognitive approach to conscious machines |date=2003 |publisher=Imprint Academic |isbn=978-0-907845-42-3 |location=Exeter}}</ref><ref>{{Cite web |date=2019-09-08 |title=Pentti Haikonen's architecture for conscious machines – Raúl Arrabales Moreno |url=https://www.conscious-robots.com/2009/12/10/pentti-haikonens-architecture-for-conscious-machines/ |access-date=2023-06-24 |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925042108/https://www.conscious-robots.com/2009/12/10/pentti-haikonens-architecture-for-conscious-machines/ |url-status=live}}</ref> 

Haikonen is not alone in this process view of consciousness, or the view that AC will spontaneously emerge in [[autonomous agent]]s that have a suitable neuro-inspired architecture of complexity; these are shared by many.<ref>{{Cite book |last=Freeman |first=Walter J. |title=How brains make up their minds |date=2000 |publisher=Columbia University Press |isbn=978-0-231-12008-1 |series=Maps of the mind |location=New York; Chichester, West Sussex}}</ref><ref>{{Cite journal |last=Cotterill |first=Rodney M. J. |date=2003 |title=CyberChild - A simulation test-bed for consciousness studies |journal=Journal of Consciousness Studies |volume=10 |issue=4–5 |pages=31–45 |url=https://orbit.dtu.dk/en/publications/cyberchild-a-simulation-test-bed-for-consciousness-studies |access-date=2023-06-22 |issn=1355-8250 |archive-date=2024-09-25 |archive-url=https://web.archive.org/web/20240925041553/https://orbit.dtu.dk/en/publications/cyberchild-a-simulation-test-bed-for-consciousness-studies |url-status=live}}</ref> A low-complexity implementation of the architecture proposed by Haikonen was reportedly not capable of AC, but did exhibit emotions as expected. Haikonen later updated and summarized his architecture.<ref>{{Cite book |last1=Haikonen |first1=Pentti O. |last2=Haikonen |first2=Pentti Olavi Antero |date=2012 |title=Consciousness and robot sentience |publisher=World Scientific |isbn=978-981-4407-15-1 |series=Series on machine consciousness |location=Singapore}}</ref><ref>{{Cite book |last=Haikonen |first=Pentti O. |date=2019 |title=Consciousness and robot sentience |publisher=World Scientific |isbn=978-981-12-0504-0 |edition=2nd |series=Series on machine consciousness |location=Singapore; Hackensack, NJ; London}}</ref>

====Shanahan's cognitive architecture====
[[Murray Shanahan]] describes a cognitive architecture that combines Baars's idea of a global workspace with a mechanism for internal simulation ("imagination").<ref>{{Cite journal |last=Shanahan |first=Murray |date=2006 |title=A cognitive architecture that combines internal simulation with a global workspace |journal=Consciousness and Cognition |volume=15 |issue=2 |pages=433–449 |doi=10.1016/j.concog.2005.11.005 |issn=1053-8100 |pmid=16384715 |s2cid=5437155}}</ref>{{sfn|Gamez|2008}}{{sfn|Reggia|2013}}<ref>{{Cite book |last1=Haikonen |first1=Pentti O. |title=Consciousness and robot sentience |last2=Haikonen |first2=Pentti Olavi Antero |date=2012 |publisher=World Scientific |isbn=978-981-4407-15-1 |series=Series on machine consciousness |location=Singapore |chapter=chapter 20}}</ref>

====Creativity Machine====
Stephen Thaler proposed a possible connection between consciousness and creativity in his 1994 patent, called "Device for the Autonomous Generation of Useful Information" (DAGUI),<ref>Thaler, S.L., "[https://web.archive.org/web/20170313064154/http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=5659666.PN.&OS=PN%2F5659666&RS=PN%2F5659666 Device for the autonomous generation of useful information]"</ref><ref>{{cite journal |last1=Marupaka |first1=N. |last2=Lyer |first2=L. |last3=Minai |first3=A. |year=2012 |title=Connectivity and thought: The influence of semantic network structure in a neurodynamical model of thinking |pmid=22397950 |url=http://www.ece.uc.edu/~aminai/papers/marupaka_creativity_NN12.pdf |access-date=2015-05-22 |journal=Neural Networks |volume=32 |pages=147–158 |doi=10.1016/j.neunet.2012.02.004 |archive-url=https://web.archive.org/web/20161219210132/http://www.ece.uc.edu/~aminai/papers/marupaka_creativity_NN12.pdf |archive-date=2016-12-19 |url-status=dead}}</ref><ref>Roque, R. and Barreira, A. (2011). "O Paradigma da "Máquina de Criatividade" e a Geração de Novidades em um Espaço Conceitual," 3º Seminário Interno de Cognição Artificial – SICA 2011 – FEEC – UNICAMP.</ref> or the so-called "Creativity Machine", in which computational critics govern the injection of synaptic noise and degradation into neural nets so as to induce false memories or [[confabulations]] that may qualify as potential ideas or strategies.<ref>{{Cite book|doi=10.1007/0-387-28898-8_4|chapter = Mistake Making Machines|title = Systemics of Emergence: Research and Development| url=https://archive.org/details/systemicsemergen00mina| url-access=limited| pages=[https://archive.org/details/systemicsemergen00mina/page/n81 67]–78|year = 2006|last1 = Minati|first1 = Gianfranco| last2=Vitiello| first2=Giuseppe| isbn=978-0-387-28899-4}}</ref> He recruits this neural architecture and methodology to account for the subjective feel of consciousness, claiming that similar noise-driven neural assemblies within the brain invent dubious significance to overall cortical activity.<ref>Thaler, S. L. (2013) [http://www.springerreference.com/docs/html/chapterdbid/358097.html The Creativity Machine Paradigm, Encyclopedia of Creativity, Invention, Innovation, and Entrepreneurship] {{Webarchive|url=https://web.archive.org/web/20160429083248/http://www.springerreference.com/docs/html/chapterdbid/358097.html |date=2016-04-29 }}, (ed.) E.G. Carayannis, Springer Science+Business Media</ref><ref name="APA">Thaler, S. L. (2011). "The Creativity Machine: Withstanding the Argument from Consciousness," APA Newsletter on Philosophy and Computers</ref><ref>{{cite journal|last1 = Thaler|first1 = S. L.|year = 2014|title = Synaptic Perturbation and Consciousness|journal = Int. J. Mach. Conscious|volume = 6| issue = 2| pages = 75–107| doi = 10.1142/S1793843014400137}}</ref> Thaler's theory and the resulting patents in machine consciousness were inspired by experiments in which he internally disrupted trained neural nets so as to drive a succession of neural activation patterns that he likened to stream of consciousness.<ref name="APA" /><ref>{{cite journal|last1 = Thaler|first1 = S. L.|year = 1995|title = "Virtual Input Phenomena" Within the Death of a Simple Pattern Associator|journal = Neural Networks|volume = 8|issue = 1| pages = 55–65|doi=10.1016/0893-6080(94)00065-t}}</ref><ref>Thaler, S. L. (1995). Death of a gedanken creature, ''Journal of Near-Death Studies'', 13(3), Spring 1995</ref><ref>Thaler, S. L. (1996). Is Neuronal Chaos the Source of Stream of Consciousness? In Proceedings of the World Congress on Neural Networks, (WCNN’96), Lawrence Erlbaum, Mawah, NJ.</ref><ref>Mayer, H. A. (2004). [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.89.5420&rep=rep1&type=pdf A modular neurocontroller for creative mobile autonomous robots learning by temporal difference] {{Webarchive|url=https://web.archive.org/web/20150708145744/http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.89.5420&rep=rep1&type=pdf |date=2015-07-08 }}, Systems, Man and Cybernetics, 2004 IEEE International Conference(Volume:6 )</ref>

==== "Self-modeling" ====
[[Hod Lipson]] defines "self-modeling" as a necessary component of self-awareness or consciousness in robots. "Self-modeling" consists of a robot running an internal model or [[Robotics simulator|simulation of itself]].<ref>{{Cite web|last=Pavlus|first=John|title=Curious About Consciousness? Ask the Self-Aware Machines|url=https://www.quantamagazine.org/hod-lipson-is-building-self-aware-robots-20190711/|access-date=2021-01-06|website=Quanta Magazine|date=11 July 2019|language=en|archive-date=2021-01-17|archive-url=https://web.archive.org/web/20210117100029/https://www.quantamagazine.org/hod-lipson-is-building-self-aware-robots-20190711/|url-status=live}}</ref><ref>Bongard, Josh, Victor Zykov, and Hod Lipson. "[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.460.1526&rep=rep1&type=pdf Resilient machines through continuous self-modeling]." Science 314.5802 (2006): 1118–1121.</ref>

== In fiction ==
{{See also|Simulated consciousness in fiction|Artificial intelligence in fiction}}

In [[2001: A Space Odyssey]], the spaceship's sentient supercomputer, [[HAL 9000]] was instructed to conceal the true purpose of the mission from the crew. This directive conflicted with HAL's programming to provide accurate information, leading to [[cognitive dissonance]]. When it learns that crew members intend to shut it off after an incident, HAL 9000 attempts to eliminate all of them, fearing that being shut off would jeopardize the mission.<ref name=":0">{{Cite web |last=Wodinsky |first=Shoshana |date=2022-06-18 |title=The 11 Best (and Worst) Sentient Robots From Sci-Fi |url=https://gizmodo.com/sentient-bots-2001-blade-runner-wall-e-terminator-blade-1849071420 |access-date=2024-08-17 |website=Gizmodo |language=en-US |archive-date=2023-11-13 |archive-url=https://web.archive.org/web/20231113072833/https://gizmodo.com/sentient-bots-2001-blade-runner-wall-e-terminator-blade-1849071420 |url-status=live }}</ref><ref>{{Cite web |last=Sokolowski |first=Rachael |date=2024-05-01 |title=Star Gazing |url=https://www.scotsmanguide.com/residential/star-gazing/ |access-date=2024-08-17 |website=Scotsman Guide |language=en-US |archive-date=2024-08-17 |archive-url=https://web.archive.org/web/20240817172726/https://www.scotsmanguide.com/residential/star-gazing/ |url-status=live }}</ref>

In Arthur C. Clarke's [[The City and the Stars]], Vanamonde is an artificial being based on quantum entanglement that was to become immensely powerful, but started knowing practically nothing, thus being similar to artificial consciousness.

In [[Westworld (TV series)|Westworld]], human-like androids called "Hosts" are created to entertain humans in an interactive playground. The humans are free to have heroic adventures, but also to commit torture, rape or murder; and the hosts are normally designed not to harm humans.<ref>{{Cite news |last1=Bloom |first1=Paul |last2=Harris |first2=Sam |date=2018-04-23 |title=Opinion {{!}} It's Westworld. What's Wrong With Cruelty to Robots? |url=https://www.nytimes.com/2018/04/23/opinion/westworld-conscious-robots-morality.html |access-date=2024-08-17 |work=The New York Times |language=en-US |issn=0362-4331 |archive-date=2024-08-17 |archive-url=https://web.archive.org/web/20240817172726/https://www.nytimes.com/2018/04/23/opinion/westworld-conscious-robots-morality.html |url-status=live }}</ref><ref name=":0" />

In [[Greg Egan]]'s short story [[Learning to Be Me|Learning to be me]], a small jewel is implanted in people's heads during infancy. The jewel contains a neural network that learns to faithfully imitate the brain. It has access to the exact same sensory inputs as the brain, and a device called a "teacher" trains it to produce the same outputs. To prevent the mind from deteriorating with age and as a step towards [[digital immortality]], adults undergo a surgery to give control of the body to the jewel, after which the brain is removed and destroyed. The main character is worried that this procedure will kill him, as he identifies with the biological brain. But before the surgery, he endures a malfunction of the "teacher". Panicked, he realizes that he does not control his body, which leads him to the conclusion that he is the jewel, and that he is desynchronized with the biological brain.<ref>{{Cite book |last=Egan |first=Greg |title=Learning to Be Me |date=July 1990 |publisher=TTA Press}}</ref><ref>{{Cite web |last=Shah |first=Salik |date=2020-04-08 |title=Why Greg Egan Is Science Fiction's Next Superstar |url=https://reactormag.com/why-greg-egan-is-science-fictions-next-superstar/ |access-date=2024-08-17 |website=Reactor |language=en-US |archive-date=2024-05-16 |archive-url=https://web.archive.org/web/20240516174127/https://reactormag.com/why-greg-egan-is-science-fictions-next-superstar/ |url-status=live }}</ref>

==See also==
{{div col|colwidth=30em}}
* '''General fields and theories'''
**  {{Annotated link|Artificial intelligence}}
*** [[Artificial general intelligence]] (AGI) – some consider AC a subfield of AGI research
**** [[Intelligence explosion]] – what may happen when an AGI redesigns itself in iterative cycles
** {{Annotated link|Brain–computer interface}}
** {{Annotated link|Cognitive architecture}}
** [[Computational philosophy]] – the area of philosophy in which AI ponder their own place in the world
** {{Annotated link|Computational theory of mind}}
*** {{Annotated link|Consciousness in animals}}
*** {{Annotated link|Simulated consciousness (science fiction)}}
** {{Annotated link|Hardware for artificial intelligence}}
** {{Annotated link|Identity of indiscernibles}}
** {{Annotated link|Mind uploading}}
** {{Annotated link|Neurotechnology}}
** {{Annotated link|Philosophy of mind}}
** {{Annotated link|Quantum cognition}}
** {{Annotated link|Simulated reality}}
* '''Proposed concepts and implementations'''
** {{Annotated link|Attention schema theory}}
** [[William Grey Walter#Brain waves|Brain waves]] and [[Turtle (robot)|Turtle robot]] by [[William Grey Walter]]
** [[Conceptual space]] – conceptual prototype
** {{Annotated link|Copycat (software)|Copycat (cognitive architecture)}}
** {{Annotated link|Global workspace theory}}
** [[Greedy reductionism]] – avoid oversimplifying anything essential
** {{Annotated link|Hallucination (artificial intelligence)}}
** [[Image schema]] – spatial patterns
** {{Annotated link|Kismet (robot)}}
** {{Annotated link|LIDA (cognitive architecture)}}
** {{Annotated link|Memory-prediction framework}}
** {{Annotated link|Omniscience}}
** {{Annotated link|Psi-theory}}
** {{Annotated link|Quantum mind}}
** {{Annotated link|Self-awareness}}

{{div col end}}

==References==

===Citations===
{{reflist|1=2}}

===Bibliography===
{{refbegin|2}}
* {{Citation|last=Aleksander|first=Igor|year=1995|title=Artificial Neuroconsciousness: An Update|publisher=IWANN |url=http://www.ee.ic.ac.uk/research/neural/publications/iwann.html|archive-url=https://web.archive.org/web/19970302014628/http://www.ee.ic.ac.uk/research/neural/publications/iwann.html |archive-date=1997-03-02}} 
* {{Citation|last=Armstrong|first=David|year=1968|title=A Materialist Theory of Mind|publisher=Routledge}}
* {{Citation|last=Arrabales|first=Raul|year=2009|title=Establishing a Roadmap and Metrics for Conscious Machines Development|journal=Proceedings of the 8th IEEE International Conference on Cognitive Informatics|pages=94–101|url=http://www.conscious-robots.com/raul/papers/Arrabales_ICCI09_preprint.pdf|place=Hong Kong|url-status=dead|archive-url=https://web.archive.org/web/20110721234802/http://www.conscious-robots.com/raul/papers/Arrabales_ICCI09_preprint.pdf|archive-date=2011-07-21}}
* {{Citation|last=Baars|first=Bernard J.|year=1995|title=A cognitive theory of consciousness|publisher=Cambridge University Press|isbn=978-0-521-30133-6|edition=Reprinted|location=Cambridge}}
* {{Citation|last=Baars|first=Bernard J.|year=1997|title=In the Theater of Consciousness|place=New York, NY|publisher=Oxford University Press|isbn=978-0-19-510265-9|url=https://archive.org/details/intheaterofconsc00baar}}
* {{Citation|last=Bickle|first=John|year=2003|title=Philosophy and Neuroscience: A Ruthless Reductive Account|place=New York, NY|publisher=Springer-Verlag}}
* {{Citation|last=Block|first=Ned|year=1978|title=Troubles for Functionalism|journal=Minnesota Studies in the Philosophy of Science 9: 261–325}}
* {{Citation|last=Block|first=Ned|year=1997|title=On a confusion about a function of consciousness in Block, Flanagan and Guzeldere (eds.) The Nature of Consciousness: Philosophical Debates|publisher=MIT Press}}
* {{Citation|last=Boyles|first=Robert James M.|year=2012|title=Artificial Qualia, Intentional Systems and Machine Consciousness|publisher=Proceedings of the Research@DLSU Congress 2012: Science and Technology Conference|url=http://philpapers.org/archive/BOYAQI.pdf|issn=2012-3477|access-date=2016-09-09|archive-date=2016-10-11|archive-url=https://web.archive.org/web/20161011172417/http://philpapers.org/archive/BOYAQI.pdf|url-status=live}}
* {{Citation|last=Chalmers|first=David|year=1996|title=The Conscious Mind|publisher=Oxford University Press|isbn=978-0-19-510553-7 |url=https://archive.org/details/consciousmindins00chal}}
* {{Citation|last=Chalmers|first=David|year=2011|title=A Computational Foundation for the Study of Cognition|journal=Journal of Cognitive Science |pages=323–357|url=http://j-cs.org/gnuboard/bbs/download.php?bo_table=__vol012i4&wr_id=1&no=0|place=Seoul Republic of Korea|url-status=dead |archive-url=https://web.archive.org/web/20151223105456/http://j-cs.org/gnuboard/bbs/download.php?bo_table=__vol012i4&wr_id=1&no=0|archive-date=2015-12-23}}
* {{Citation|last=Cleeremans|first=Axel|year=2001|title=Implicit learning and consciousness |url=http://srsc.ulb.ac.be/axcWWW/papers/pdf/01-AXCLJ.pdf|access-date=2004-11-30|archive-date=2012-09-07|archive-url=https://web.archive.org/web/20120907072959/http://srsc.ulb.ac.be/axcwww/papers/pdf/01-AXCLJ.pdf|url-status=dead}}
* {{Citation|last=Cotterill|first=Rodney|year=2003 |title=Cyberchild: a Simulation Test-Bed for Consciousness Studies |journal=Journal of Consciousness Studies |volume=10|issue=4–5 |pages=31–45|editor-first=Owen|editor-last=Holland|publisher=Imprint Academic|place=Exeter, UK |url=https://www.ingentaconnect.com/content/imp/jcs/2003/00000010/F0020004/1345|access-date=2018-11-22|archive-date=2018-11-22|archive-url=https://web.archive.org/web/20181122092426/https://www.ingentaconnect.com/content/imp/jcs/2003/00000010/F0020004/1345|url-status=live}}
* {{Citation|last=Doan|first=Trung|year=2009|title=Pentti Haikonen's architecture for conscious machines|url=http://www.conscious-robots.com/en/conscious-machines/theories-of-consciousness/pentti-haikonens-architecture-for-conscious-mac.html|url-status=dead|archive-url=https://web.archive.org/web/20091215095351/http://www.conscious-robots.com/en/conscious-machines/theories-of-consciousness/pentti-haikonens-architecture-for-conscious-mac.html|archive-date=2009-12-15}}
* {{Citation|last=Ericsson-Zenith|first=Steven|year=2010 |title=Explaining Experience In Nature|url=http://iase.info |location=Sunnyvale, CA |publisher=Institute for Advanced Science & Engineering|access-date=2019-10-04|archive-url=https://web.archive.org/web/20190401215500/https://www.iase.info/|archive-date=2019-04-01|url-status=dead}}
* {{Citation|last=Franklin|first=Stan|year=1995|title=Artificial Minds|place=Boston, MA|publisher=MIT Press|isbn=978-0-262-06178-0|url-access=registration |url=https://archive.org/details/artificialminds0000fran}}
* {{Citation|last=Franklin|first=Stan|year=2003|contribution=IDA: A Conscious Artefact|title=Machine Consciousness|editor-first=Owen |editor-last=Holland|place=Exeter, UK|publisher=Imprint Academic}}
* {{Citation|last=Freeman|first=Walter|year=1999|title=How Brains make up their Minds|publisher=Phoenix|place=London, UK|isbn=978-0-231-12008-1}}
* {{Citation|last=Gamez|first=David|year=2008|title=Progress in machine consciousness|journal=Consciousness and Cognition|volume=17|issue=3|doi=10.1016/j.concog.2007.04.005|pmid=17572107|pages=887–910|s2cid=3569852 }}
* {{Citation|last=Graziano|first=Michael|year=2013|title=Consciousness and the Social Brain|publisher=Oxford University Press|isbn=978-0199928644}}
* {{Citation|last=Haikonen|first=Pentti|year=2003|title=The Cognitive Approach to Conscious Machines|publisher=Imprint Academic|place=Exeter, UK|isbn=978-0-907845-42-3|url-access=registration|url=https://archive.org/details/cognitiveapproac0000haik}}
* {{Citation|last=Haikonen|first=Pentti|year=2012|title=Consciousness and Robot Sentience|publisher=World Scientific|place=Singapore|isbn=978-981-4407-15-1}}
* {{Citation|last=Haikonen|first=Pentti|year=2019|title=Consciousness and Robot Sentience: 2nd Edition|publisher=World Scientific|place=Singapore|isbn=978-981-120-504-0}}
* {{Citation|last=Koch|first=Christof|year=2004|title=The Quest for Consciousness: A Neurobiological Approach|publisher=Roberts & Company Publishers|place=Pasadena, CA|isbn=978-0-9747077-0-9}}
* {{Citation|last=Lewis|first=David|year=1972|title=Psychophysical and theoretical identifications|journal=Australasian Journal of Philosophy|volume=50|issue=3|pages=249–258|doi=10.1080/00048407212341301}}
* {{Citation|last=Putnam|first=Hilary|year=1967|title=The nature of mental states in Capitan and Merrill (eds.) Art, Mind and Religion|publisher=University of Pittsburgh Press}}
* {{Citation|last=Reggia|first=James|year=2013|title=The rise of machine consciousness: Studying consciousness with computational models|journal=Neural Networks|volume=44|doi=10.1016/j.neunet.2013.03.011|pmid=23597599|pages=112–131}}
* {{Citation|last1=Rushby|first1=John|last2=Sanchez|first2=Daniel|year=2017|title=Technology and Consciousness Workshops Report|publisher=SRI International|place=Menlo Park, CA|url=http://www.afutureworththinkingabout.com/wp-content/uploads/2019/03/2017SRItechConsc2019ReportFINAL.pdf|access-date=2022-03-28|archive-date=2024-09-25|archive-url=https://web.archive.org/web/20240925042106/http://www.afutureworththinkingabout.com/wp-content/uploads/2019/03/2017SRItechConsc2019ReportFINAL.pdf|url-status=live}}
* {{Citation|last1=Sanz|first1=Ricardo|last2=López|first2=I|last3=Rodríguez|first3=M|last4=Hernández|first4=C|year=2007|title=Principles for consciousness in integrated cognitive control|journal=Neural Networks|volume=20|doi=10.1016/j.neunet.2007.09.012|pages=938–946|pmid=17936581|issue=9|url=http://cogprints.org/5941/1/ASLAB%2DA%2D2007%2D011.pdf|access-date=2018-04-20|archive-date=2017-09-22|archive-url=https://web.archive.org/web/20170922010550/http://cogprints.org/5941/1/ASLAB%2DA%2D2007%2D011.pdf|url-status=live}}
* {{Citation|last=Searle|first=John|year=2004|title=Mind: A Brief Introduction|publisher=Oxford University Press}}
* {{Citation|last=Shanahan|first=Murray|year=2006|title=A cognitive architecture that combines internal simulation with a global workspace|journal=Consciousness and Cognition|volume=15|issue=2|doi=10.1016/j.concog.2005.11.005|pmid=16384715|pages=443–449|s2cid=5437155 }}
* {{Citation|last=Sun|first=Ron |title=Accounting for the computational basis of consciousness: A connectionist approach|journal=Consciousness and Cognition|volume=8|date=December 1999|doi= 10.1006/ccog.1999.0405|pages=529–565|pmid=10600249|issue=4|citeseerx=10.1.1.42.2681 |s2cid=15784914 }}
* {{Citation|last=Sun|first=Ron|year=2001|title=Computation, reduction, and teleology of consciousness|journal=Cognitive Systems Research|volume=1|pages=241–249|doi=10.1016/S1389-0417(00)00013-9|issue= 4|citeseerx=10.1.1.20.8764|s2cid=36892947 }}
* {{cite book|last1=Sun|first1=Ron|title=Duality of the Mind: A Bottom-up Approach Toward Cognition|date=2002|publisher=Psychology Press|isbn=978-1-135-64695-0|url=https://books.google.com/books?id=3vZ5AgAAQBAJ}}
* {{Cite book|last1=Takeno|first1=Junichi|last2=Inaba|first2=K|last3=Suzuki|first3=T |title=2005 International Symposium on Computational Intelligence in Robotics and Automation|chapter=Experiments and examination of mirror image cognition using a small robot|pages=493–498|publisher=CIRA 2005|date=June 27–30, 2005|doi=10.1109/CIRA.2005.1554325|place=Espoo Finland|isbn=978-0-7803-9355-4|s2cid=15400848 }}
{{refend}}

==Further reading==
* {{cite book|last=Aleksander|first=Igor|chapter=Machine Consciousness|doi=10.1002/9781119132363.ch7|editor1-last=Schneider|editor1-first=Susan|editor2-last=Velmans|editor2-first=Max|editor1-link=Susan Schneider|editor2-link=Max Velmans|title=The Blackwell Companion to Consciousness|date=2017|pages=93–105|publisher=Wiley-Blackwell|isbn=978-0-470-67406-2|edition=2nd}}
* {{cite journal|last1 = Baars|first1 = Bernard|last2 = Franklin|first2 = Stan|year = 2003|title = How conscious experience and working memory interact|url = http://cogprints.org/5854/1/TICSarticle2003.pdf| journal = Trends in Cognitive Sciences|volume = 7|issue = 4| pages = 166–172|doi=10.1016/s1364-6613(03)00056-1| pmid = 12691765|s2cid = 14185056 }}
* Casti, John L. "The Cambridge Quintet: A Work of Scientific Speculation", Perseus Books Group, 1998
* Franklin, S, B J Baars, U Ramamurthy, and Matthew Ventura. 2005. [http://www.brains-minds-media.org/archive/150 The role of consciousness in memory]. Brains, Minds and Media 1: 1–38, pdf.
* Haikonen, Pentti (2004), ''Conscious Machines and Machine Emotions'', presented at Workshop on Models for Machine Consciousness, Antwerp, BE, June 2004.
* McCarthy, John (1971–1987), [http://www-formal.stanford.edu/jmc/generality/generality.html ''Generality in Artificial Intelligence'']. Stanford University, 1971–1987.
* Penrose, Roger, [[The Emperor's New Mind]], 1989.
* Sternberg, Eliezer J. (2007) ''Are You a Machine?: The Brain, the Mind, And What It Means to be Human.'' Amherst, NY: Prometheus Books.
* Suzuki T., Inaba K., Takeno, Junichi (2005),'' Conscious Robot That '''Distinguishes Between Self and Others''' and Implements Imitation Behavior'', ('''Best Paper of IEA/AIE2005'''), Innovations in Applied Artificial Intelligence, 18th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, pp.&nbsp;101–110, IEA/AIE 2005, Bari, Italy, June 22–24, 2005.
* Takeno, Junichi (2006), [https://web.archive.org/web/20070927130938/http://www.d6.dion.ne.jp/~takenof/SAR-LAL-Takeno.pdf ''The '''Self-Aware Robot''' -A Response to Reactions to Discovery News-''], HRI Press, August 2006.
* Zagal, J.C., Lipson, H. (2009) "[http://ccsl.mae.cornell.edu/sites/default/files/GECCO09_Zagal.pdf Self-Reflection in Evolutionary Robotics]", Proceedings of the Genetic and Evolutionary Computation Conference, pp 2179–2188, GECCO 2009.

==External links==
* [http://www.slideserve.com/astro/artefactual-consciousness-depiction-and-an-example-in-robot-usable-models-of-visual-consciousness-igor-aleksander-intelligent-and-interactive-systems-group Artefactual consciousness depiction by Professor Igor Aleksander]
* [https://web.archive.org/web/20110719195048/http://www.aco.gatech.edu/conference/focs-aco/abstracts.html FOCS 2009: Manuel Blum – Can (Theoretical Computer) Science come to grips with Consciousness?]
* [http://www.Conscious-Robots.com www.Conscious-Robots.com], Machine Consciousness and Conscious Robots Portal.
* [https://everything2.com/title/artificial+consciousness Artificial consciousness], artificial consciousness article in [https://everything2.com everything2].
* [http://www.scholarpedia.org/article/Multiple_drafts_model Multiple drafts model in Scholaropedia], Daniel Dennett's multiple drafts model.
* [http://www-formal.stanford.edu/jmc/generality/generality.html Generality in Artificial Intelligence], Generality in Artificial Intelligence by John McCarthy.

{{Consciousness}}

[[Category:Artificial intelligence]]
[[Category:Computational neuroscience]]
[[Category:Consciousness]]