The Ethics Blog

A research blog from the Centre for Resarch Ethics & Bioethics (CRB)

Tag: neuroethics (Page 1 of 10)

Artificial consciousness – a look behind the hopeful facade

Image by Gerd Altman on Pixabay
16 June, 2026 / / 3 Comments

During the 20th century, it was often considered scientifically suspect to talk about consciousness or to use psychological concepts that were not defined in terms of observable behavior. For even longer periods, consciousness, or the soul, was attributed only to some humans who in turn guarded the concept very carefully so that it did not risk being transferred to “others” (at least not fully). Against this background, it is surprising to note how the possibility of conscious machines has suddenly begun to be considered an important scientific question. In some cases, artificial consciousness is even treated as a strategic goal to be realized through new research efforts. Where does this sudden hopefulness about conscious AI come from, when consciousness was previously surrounded by strict skepticism and border control?

In an article, Kathinka Evers takes us behind the hopeful facade. Where does this unexpected optimism come from? Have we become more open-minded lately? Perhaps partly, answers Kathinka Evers, but the optimism about machine consciousness may also be a new form of human self-aggrandizement. How so? If we humans (or some human group) could produce artificial consciousness, we (or that group) would resemble the creator god that humans have long believed made them in his image. We (or that group) would take over the top position that humans have submitted to for millennia.

The hopefulness probably also reflects notions that machine consciousness could give artificial systems even more powerful capabilities that humanity could benefit from, writes Kathinka Evers. Conscious AI could make complex decisions that consciously consider human values ​​and moral norms. It could protect us better than we can protect ourselves. That certainly sounds hopeful. But given that we are already programming drones and missiles to harm and kill people – in accordance with human values ​​and norms – we should probably examine ourselves more carefully before we place too much faith in our machine images. Could they possibly create even greater threats rather than protect us from them?

Humans are contradictory. We are as compassionate as we are insensitive. Our sympathies for each other are selective and have made human groups in most cultures and historical periods violent and destructive towards other ethnic groups, towards women, towards the poor, towards other species, writes Kathinka Evers. The border surveillance of the concept of consciousness (or the soul) to ensure exclusivity is just one of many examples of this tendency to unite by distinguishing. Human values ​​and norms separate us from each other as much as they connect us. Wouldn’t artificial consciousness, created in our image, also multiply our human conflicts? Should we rather hope that conscious AI – if it were possible – is not aligned with human values and moral norms?

If you want to travel further behind the hopeful facade, read the article here: Artificial Consciousness: Science Fiction, Utopia, or Pandora’s Box? Kathinka Evers also discusses whether artificial consciousness can be considered a possibility, how such consciousness could be detected, and what research into artificial consciousness can actually teach us. Perhaps it is rather that through such research we would learn more about ourselves and return from the detour much wiser?

Pär Segerdahl

Written by…

Pär Segerdahl, Associate Professor at the Centre for Research Ethics & Bioethics and editor of the Ethics Blog.

Evers, K. (2026). Artificial Consciousness: Science Fiction, Utopia, or Pandora’s Box? In Proceedings of the Paris Institute for Advanced Study (Vol. 27). https://doi.org/10.5281/zenodo.20267984

This post in Swedish

We like challenging questions

Taking the science of consciousness to the clinic is a collective endeavor

24 February, 2026 / / 1 Comment

“Consciousness” is an ambiguous concept that arouses the interest of people with different expertise, including the general public. This situation naturally creates several related ambiguities, for example about how consciousness should be understood scientifically and how we can explain it. Not least, it creates uncertainties about how we can translate the scientific knowledge we have about consciousness to the clinics.

How do we best develop our understanding of consciousness and how do we make current knowledge in the field practically useful? In an article recently published in Neuroscience & Biobehavioral Reviews, we propose a model that combines theoretical reflection, empirical research, ethical analysis, and clinical translation. Our article, Advancing the science of consciousness: from ethics to clinical care, starts from the fundamental question of how to translate significant advances in the neurobiological study of consciousness into clinical settings. A first step towards answering this question is to identify the obstacles that need to be overcome. We focus on two main obstacles: the lack of a generally agreed-upon working definition of consciousness, and the lack of consensus on how to identify reliable markers that indicate the presence of consciousness.

The article is the result of a multi-year collaboration between experts from various fields, including philosophy, ethics, medicine, clinical, cognitive, and computational neuroscience, as well as representatives of patient associations. The research described in the article focuses on disorders of consciousness (DoCs), that is, the impaired mental condition of patients with traumatic or non-traumatic brain injuries. The prevalence of this severe medical condition is quite high, the rate of misdiagnosis is fairly alarming, and treatment options are still limited.

Following a traumatic or non-traumatic brain injury, the patient may enter into a state of coma where they are completely unresponsive and lack the two main clinical dimensions of consciousness: wakefulness (related to the level of consciousness) and awareness (related to the content of consciousness). In the article, we leave aside the big controversy about the definition of consciousness and propose that a clinically useful choice is to treat consciousness as a combination of wakefulness and awareness. This pragmatic choice will allow us to improve the clinical treatment of patients with DoCs and, consequently, their well-being.

We further describe behavioral, physiological, and computational markers and measures that recent research indicates are very promising for formulating more precise and reliable diagnoses of various disorders of consciousness. Such a combination of approaches is recommended in the international guidelines on DoCs to reduce the still too high rate of misdiagnoses. Yet, there are still concerns about whether the available measures are effective and whether they cover the full spectrum of consciousness. Therefore, researchers are striving to identify additional approaches and indicators. In the article, we propose that patients’ ability to perceive illusions and respond accordingly can be used to assess their capacity for conscious experience. We also propose that virtual reality can be used to detect residual consciousness and improve interaction with patients affected by DoCs.

Technological advances alone cannot improve the current state of consciousness science. To identify the most effective strategies for translating scientific findings into better healthcare, technological advances must be combined with ethical reflection. The ethical issues related to DoCs are numerous. In the article, we focus on some of them to illustrate the need for continued dialogue between different disciplines and stakeholders, including researchers, clinicians, and patient representatives. We analyze, among other things, misdiagnosis, as well as the risk that by using “healthy” consciousness as the norm for what consciousness is, we may neglect the possibility that patients with DoCs retain forms of consciousness that do not conform to the norm. We also analyze uncertainties about how these patients are classified, as well as the need for better involvement of family members, for example through improved communication and information exchange about the patients’ condition that can help clinicians make the most appropriate decisions. Furthermore, we analyze the promise of neurorehabilitation and neuropalliative care for these patients. Since the inspiration of our ethical reflection in the article is pragmatic and action-oriented, we conclude by proposing an actionable model that clearly identifies and assigns specific responsibilities to different actors (such as institutions, researchers, clinicians, and family members).

While we cannot claim to resolve all relevant issues, the collaboration behind this article can serve as a model for how to approach the challenges. A multidisciplinary, multi-perspective approach involving different disciplines and stakeholders is needed to improve the prognosis and quality of life for patients with disorders of consciousness. It is needed also to empower family members with the knowledge and capacity they need to participate in the clinical care of their loved ones.

Finally, our article is defined as a “live paper,” because the reader can access a number of interactive tools online on the research platform Ebrains, including datasets, computational models, and figures.

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

Michele Farisco, Kathinka Evers, Jitka Annen, et al. Advancing the science of consciousness: from ethics to clinical care, Neuroscience & Biobehavioral Reviews, Volume 180, 2026, https://doi.org/10.1016/j.neubiorev.2025.106497

We transcend disciplinary borders

When we ourselves contribute to the problem: a retrospective view of resignation syndrome

Child sleeping on bed. Photo by Annie Spratt, Unsplash
13 January, 2026 / / 1 Comment

Humans are good at solving problems. But solutions also cause unforeseen problems. The latter problems can be more difficult to understand because they are so close to us: we do not see how we ourselves create them through our solutions. A person who feels that no one smiles at her may be unaware of how she herself never smiles but observes her surroundings with a demonstratively stern look, as if that could help: “Why should I smile when my so-called fellow human beings never do? They are the problem, not me!” In retrospect, we can more easily see and admit how we ourselves contributed to the problem by our way of solving it. But try to overview similar patterns while being part of them and actively considering everything from your perspective!

So-called resignation syndrome in refugee children, which affected more than 1,000 children during more than two decades, is now history. In a new article, Karl Sallin looks back at the rise and fall of the illness, which manifested itself as loss of physical and mental functions. The children who were affected could neither move nor communicate, but were bedridden and needed tube feeding. The prevailing problem analysis was that the condition was caused by trauma and stress, not least the stress of living under the threat of not getting a residency permit, and that the children’s defeatism took on these physical and mental expressions. In the search for an effective treatment, it was therefore assumed that the children needed security in order to recover: security in the form of closeness to the family and a residence permit. Therefore, the care of the children was handed over to the parents and residence permits began to be used as part of the treatment. The syndrome, which showed no signs of subsiding but, on the contrary, continued to engage and be discussed in the media, however, exhibited a strange pattern. The illness only affected refugee children in Sweden, and moreover children mainly from states in the former Yugoslavia and states in the former Soviet Union. If the problem analysis was correct, then refugee children in countries other than Sweden should also exhibit the symptoms, since they have experienced similar forms of trauma and stress. Nor should refugee children from states in the former Yugoslavia and Soviet Union be overrepresented.

Karl Sallin describes how the treatment of resignation syndrome changed over time. The change was partly related to the syndrome’s nation-bound pattern, partly to the discovery of some cases of child abuse and simulation. Although trauma and stress contributed to the symptoms, it became clearer over time that the syndrome was probably also related to other and more decisive factors. The asylum process was separated from treatment and a child protection focus meant that the child was often separated from the family. This proved effective, and what Karl Sallin calls a culture-bound endemic soon ebbed away.

In retrospect, the pattern of the syndrome can be more easily seen. It becomes clearer how a link between symptoms and residence permit, as well as colorful media stories about the disease, could not only encourage simulation, but also create strong disease expectations in refugee children and their families that actually caused life-threatening conditions. Think of the placebo and nocebo effects, where deep expectations cause recovery or disease. Karl Sallin therefore argues that even if cases of simulation were discovered, refugee children really became life-threateningly ill because of the way resignation syndrome was diagnosed, debated and treated in Sweden. Human expectations are not to be trifled with, but both the treatment of the syndrome and the media stories about it seem to have done so. Is the general pattern familiar?

Karl Sallin suggests that resignation syndrome requires a constructivist perspective on illness in order to be understandable, and that the label, diagnosis and treatment probably caused harm. To avoid similar events in the future, greater awareness is needed of how our ways of labeling, diagnosing, treating and narrating illness can also contribute to illness, he writes. Given medicine’s duty not to harm, such awareness is essential.

The article concludes with the suggestion that it would be reasonable to withdraw the resignation syndrome diagnosis now that it is no longer serves its purposes. Read the article here: Looking back at resignation syndrome: the rise and fall of a culture-bound endemic.

Pär Segerdahl

Written by…

Pär Segerdahl, Associate Professor at the Centre for Research Ethics & Bioethics and editor of the Ethics Blog.

Sallin, K. Looking back at resignation syndrome: the rise and fall of a culture-bound endemic. Philosophy Ethics and Humanities in Medicine 20, 41 (2025). https://doi.org/10.1186/s13010-025-00209-8

This post in Swedish

We challenge habits of thought

How to tell if AI has feelings when it is designed to reflect human traits?

woman looking in mirror, photo by Ismael Sanchez from Pexels
21 October, 2025 / / 1 Comment

Debates about the possibility that artificial systems can develop the capacity for subjective experiences are becoming increasingly common. Indeed, the topic is fascinating and the discussion is gaining interest also from the public. Yet the risk of ideological and imaginative rather than scientific and rational reflections is quite high. Several factors make the idea of engineering subjective experience, such as developing sensitive robots, either very attractive or extremely frightening. How can we avoid getting stuck in either of these, in my opinion, equally unfortunate extremes? I believe we need a balanced and “pragmatic” analysis of both the logical conceivability and the technical feasibility of artificial consciousness. This is what we are trying to do at CRB within the framework of the CAVAA project.

In this post, I want to illustrate what I mean by a pragmatic analysis by summarizing an article I recently wrote together with Kathinka Evers. We review five strategies that researchers in the field have developed to address the issue whether artificial systems may have the capacity for subjective experiences, either positive experiences such as pleasure or negative ones such as pain. This issue is challenging when it comes to humans and other animals, but becomes even more difficult for systems whose nature, architecture, and functions are very different from our own. In fact, there is an additional challenge that may be particularly tricky when it comes to artificial systems: the gaming problem. The gaming problem has to do with the fact that artificial systems are trained with human-generated data to reflect human traits. Functional and behavioral markers of sentience are therefore unreliable and cannot be considered evidence of subjective experience.

We identify five strategies in the literature that may be used to face this challenge. A theory-based strategy starts from selected theories of consciousness to derive relevant indicators of sentience (structural or functional features that indicate conscious capacities), and then checks whether artificial systems exhibit them. A life-based strategy starts from the connection between consciousness and biological life; not to rule out that artificial systems can be conscious, but to argue that they must be alive in some sense in order to possibly be conscious. A brain-based strategy starts from the features of the human brain that we have identified as crucial for consciousness to then check whether artificial systems possess them or similar ones. A consciousness-based strategy searches for other forms of biological consciousness besides human consciousness, to identify what (if anything) is truly indispensable for consciousness and what is not. In this way, one aims to overcome the controversy between the many theories of consciousness and move towards identifying reliable evidence for artificial consciousness. An indicator-based strategy develops a list of indicators, features that we tend to agree characterize conscious experience, and which can be seen as indicative (probabilistic rather than definitive evidence) of the presence of consciousness in artificial systems.

In the article we describe the advantages and disadvantages of the five strategies above. For example, the theory-based strategy has the advantage of a broad base of empirically validated theories, but it is necessarily selective with respect to which theories individual proponents of the strategy draw upon. The life-based approach has the advantage of starting from the well-established fact that all known examples of conscious systems are biological, but it can be interpreted as ruling out, from the outset, the possibility of alternative forms of AI consciousness beyond the biological ones. The brain-based strategy has the advantage of being based on empirical evidence about the brain bases of consciousness. It avoids speculation about hypothetical alternative forms of consciousness, and it is pragmatic in the sense that it translates into specific approaches to testing machine consciousness. However, because the brain-based approach is limited to human-like forms of consciousness, it may lead to overlooking alternative forms of machine consciousness. The consciousness-based strategy has the advantage of avoiding anthropomorphic and anthropocentric temptations to assume that the human form of consciousness is the only possible one. One of the shortcomings of the consciousness-based approach is that it risks addressing a major challenge (identifying AI consciousness) by taking on a possibly even greater challenge (providing a comparative understanding of different forms of consciousness in nature). Finally, the indicator-based strategy has the advantage of relying on what we tend to agree characterizes conscious activity, and of remaining neutral in relation to specific theories of consciousness: it is compatible with different theoretical accounts. Yet it has the drawback that it is developed with reference to biological consciousness, so its relevance and applicability to AI consciousness may be limited.

How can we move forward towards a good strategy for addressing the gaming problem and reliably assess subjective experience in artificial systems? We suggest that the best approach is to combine the different strategies described above. We have two main reasons for this proposal. First, consciousness has different dimensions and levels: combining different strategies increases the chances of covering this complexity. Second, to address the gaming problem, it is crucial to look for as many indicators as possible, from structural to architectural, from functional to indicators related to social and environmental dimensions. 

The question of sentient AI is fascinating, but an important reason why the question engages more and more people is probably that the systems are trained to reflect human traits. It is so easy to imagine AI with feelings! Personally, I find it at least as fascinating to contribute to a scientific and rational approach to this question. If you are interested in reading more, you can find the preprint of our article here: Is it possible to identify phenomenal consciousness in artificial systems in the light of the gaming problem?

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

Farisco, M., & Evers, K. (2025). Is it possible to identify phenomenal consciousness in artificial systems in the light of the gaming problem? https://doi.org/10.5281/zenodo.17255877

We like challenging questions

Why does science ask the question of artificial consciousness?

Two little girls facing each other. One of them is smiling and dancing, the other one has an old TV screen on her head. Photo: Ryunosuke Kikuno, from Unsplash.
4 March, 2025 / / 1 Comment

The possibility of conscious AI is increasingly perceived as a legitimate and important scientific question. This interest has arisen after a long history of scientific doubts about the possibility of consciousness not only in other animals, but sometimes even in humans. The very concept of consciousness was for a period considered scientifically suspect. But now the question of conscious AI is being raised within science.

For anyone interested in how such a mind-boggling question can be answered philosophically and scientifically, I would like to recommend an interesting AI-philosophical exchange of views in the French journal Intellectica. The exchange (which is in English) revolves around an article by two philosophers, Jonathan Birch and Kristin Andrews, who for several years have discussed consciousness not only among mammals, but also among birds, fish, cephalopods, crustaceans, reptiles, amphibians and insects. The two philosophers carefully distinguish between psychological questions about what might make us emotionally attracted to believe that an AI system is conscious, and logical questions about what philosophically and scientifically can count as evidence for conscious AI. It is to this logical perspective that they want to contribute. How can we determine whether an artificial system is truly conscious; not just be seduced into believing it because the system emotionally convincingly mirrors the behavior of subjectively experiencing humans? Their basic idea is that we should first study consciousness in a wide range of animal species beyond mammals. Partly because the human brain is too different from (today’s) artificial systems to serve as a suitable reference point, but above all because such a broad comparison can help us identify the essential features of consciousness: features that could be used as markers for consciousness in artificial systems. The two philosophers’ proposal is thus that by starting from different forms of animal consciousness, we can better understand how we should philosophically and scientifically seek evidence for or against conscious AI.

One of my colleagues at CRB, Kathinka Evers, also a philosopher, comments on the article. She appreciates Birch and Andrews’ discussion as philosophically clarifying and sees the proposal to approach the question of conscious AI by studying forms of consciousness in a wide range of animal species as well argued. However, she believes that a number of issues require more attention. Among other things, she asks whether the transition from carbon- to silicon-based substrates does not require more attention than Birch and Andrews give it.

Birch and Andrews propose a thought experiment in which a robot rat behaves exactly like a real rat. It passes the same cognitive and behavioral tests. They further assume that the rat brain is accurately depicted in the robot, neuron for neuron. In such a case, they argue, it would be inconsistent not to accept the same pain markers that apply to the rat for the robot as well. The cases are similar, they argue, the transition from carbon to silicon does not provide sufficient reason to doubt that the robot rat can feel pain when it exhibits the same features that mark pain in the real rat. But the cases are not similar, Kathinka Evers points out, because the real rat, unlike the robot, is alive. If life is essential for consciousness, then it is not inconsistent to doubt that the robot can feel pain even in this thought experiment. Someone could of course associate life with consciousness and argue that a robot rat that exhibits the essential features of consciousness must also be considered alive. But if the purpose is to identify what can logically serve as evidence for conscious AI, the problem remains, says Kathinka Evers, because we then need to clarify how the relationship between life and consciousness should be investigated and how the concepts should be defined.

Kathinka Evers thus suggests several questions of relevance to what can logically be considered evidence for conscious AI. But she also asks a more fundamental question, which can be sensed throughout her commentary. She asks why the question of artificial consciousness is even being raised in science today. As mentioned, one of Birch and Andrews’ aims was to avoid the answer being influenced by psychological tendencies to interpret an AI that convincingly reflects human emotions as if it were conscious. But Kathinka Evers asks, as I read her, whether this logical purpose may not come too late. Is not the question already a temptation? AI is trained on human-generated data to reflect human behavior, she points out. Are we perhaps seeking philosophical and scientific evidence regarding a question that seems significant simply because we have a psychological tendency to identify with our digital mirror images? For a question to be considered scientific and worth funding, some kind of initial empirical support is usually required, but there is no evidence whatsoever for the possibility of consciousness in non-living entities such as AI systems. The question of whether an AI can be conscious has no more empirical support than the question of whether volcanoes can experience their eruptions, Kathinka Evers points out. There is a great risk that we will scientifically try to answer a question that lacks scientific basis. No matter how carefully we seek the longed-for answer, the question itself seems imprudent.

I am reminded of the myth of Narcissus. After a long history of rejecting the love of others (the consciousness of others), he finally fell in love with his own (digital) reflection, tried hopelessly to hug it, and was then tormented by an eternal longing for the image. Are you there? Will the reflection respond? An AI will certainly generate a response that speaks to our human emotions.

Pär Segerdahl

Written by…

Pär Segerdahl, Associate Professor at the Centre for Research Ethics & Bioethics and editor of the Ethics Blog.

Birch Jonathan, Andrews Kristin (2024/2). To Understand AI Sentience, First Understand it in Animals. In Gefen Alexandre & Huneman Philippe (Eds), Philosophies of AI: thinking and writing with LLMs, Intellectica, 81, pp. 213-226.

Evers Kathinka (2024/2). To understand sentience in AI first understand it in animals. Commentary to Jonathan Birch and Kristin Andrews. In Gefen Alexandre & Huneman Philippe (Eds), Philosophies of AI: thinking and writing with LLMs, Intellectica, 81, pp. 229-232.

This post in Swedish

We challenge habits of thought

Conceivability and feasibility of artificial consciousness

A robot hand pointing towards a blue wall.
11 February, 2025 / / 1 Comment

Can artificial consciousness be engineered, is the endeavor even conceivable?  In a number of previous posts, I have explored the possibility of developing AI consciousness from different perspectives, including ethical analysis, a comparative analysis of artificial and biological consciousness, and a reflection about the fundamental motivation behind the development of AI consciousness.

Together with Kathinka Evers from CRB, and with other colleagues from the CAVAA project, I recently published a new paper which aims to clarify the first preparatory steps that would need to be taken on the path to AI consciousness: Preliminaries to artificial consciousness: A multidimensional heuristic approach. These first requirements are above all logical and conceptual. We must understand and clarify the concepts that motivate the endeavor. In fact, the growing discussion about AI consciousness often lacks consistency and clarity, which risks creating confusion about what is logically possible, conceptually plausible, and technically feasible.

As a possible remedy to these risks, we propose an examination of the different meanings attributed to the term “consciousness,” as the concept has many meanings and is potentially ambiguous. For instance, we propose a basic distinction between the cognitive and the experiential dimensions of consciousness: awareness can be understood as the ability to process information, store it in memory, and possibly retrieve it if relevant to the execution of specific tasks, while phenomenal consciousness can be understood as subjective experience (“what it is like to be” in a particular state, such as being in pain).

This distinction between cognitive and experiential dimensions is just one illustration of how the multidimensional nature of consciousness is clarified in our model, and how the model can support a more balanced and realistic discussion of the replication of consciousness in AI systems. In our multidisciplinary article, we try to elaborate a model that serves both as a theoretical tool for clarifying key concepts and as an empirical guide for developing testable hypotheses. Developing concepts and models that can be tested empirically is crucial for bridging philosophy and science, eventually making philosophy more informed by empirical data and improving the conceptual architecture of science.

In the article we also illustrate how our multidimensional model of consciousness can be tested empirically. We focus on awareness as a case study. As we see it, awareness has two fundamental capacities: the capacity to select relevant information from the environment, and the capacity to intentionally use this information to achieve specific goals. Basically, in order to be considered aware, the information processing should be more sophisticated than a simple input-output processing. For example, the processing needs to evaluate the relevance of information on the basis of subjective priors, such as needs and expectations. Furthermore, in order to be considered aware, information processing should be combined with a capacity to model or virtualize the world, in order to predict more distant future states. To truly be markers of awareness, these capacities for modelling and virtualization should be combined with an ability to intentionally use them for goal-directed behavior.

There are already some technical applications that exhibit capacities like these. For instance, researchers from the CAVAA project have developed a robot system which is able to adapt and correct its functioning and to learn “on the fly.” These capacities make the system able to dynamically and autonomously adapt its behavior to external circumstances to achieve its goals. This illustrates how awareness as a dimension of consciousness can already be engineered and reproduced.

Is this sufficient to conclude that AI consciousness is a fact? Yes and no. The full spectrum of consciousness has not yet been engineered and perhaps its complete reproduction is not conceivable or feasible. In fact, the phenomenal dimension of consciousness appears as a stumbling block against “full” AI consciousness. Among other things, because subjective experience arises from the capacity of biological subjects to evaluate the world, that is, to assign specific values to it on the basis of subjective needs. These needs are not just cognitive needs, as in the case of awareness, but emotionally charged and with a more comprehensive impact on the subjective state. Nevertheless, we cannot rule out this possibility a priori, and the fundamental question whether there can be a “ghost in the machine” remains open for further investigation.

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

K. Evers, M. Farisco, R. Chatila, B.D. Earp, I.T. Freire, F. Hamker, E. Nemeth, P.F.M.J. Verschure, M. Khamassi, Preliminaries to artificial consciousness: A multidimensional heuristic approach, Physics of Life Reviews, Volume 52, 2025, Pages 180-193, ISSN 1571-0645, https://doi.org/10.1016/j.plrev.2025.01.002

We like challenging questions

Why should we try to build conscious AI?

A visual interpretation of Artificial Intelligence (AI).
1 October, 2024 / / 1 Comment

In a recent post on this blog I summarized the main points of a pre-print where I analyzed the prospect of artificial consciousness from an evolutionary perspective. I took the brain and its architecture as a benchmark for addressing the technical feasibility and conceptual plausibility of engineering consciousness in artificial intelligence systems. The pre-print has been accepted and it is now available as a peer-reviewed article online.

In this post I want to focus on one particular point that I analyzed in the paper, and which I think is not always adequately accounted for in the debate about AI consciousness: what are the benefits of pursuing artificial consciousness in the first place, for science and for society at large? Why should we attempt to engineer subjective experience in AI systems? What can we realistically expect from such an endeavour?

There are several possible answers to these questions. At the epistemological level (with reference to what we can know) it is possible that developing artificial systems that replicate some features of our conscious experience could enable us to better understand biological consciousness, through similarities as well as through differences. At the technical level (with reference to what we can do) it is possible that the development of artificial consciousness would be a game-changer in AI, for instance giving AI the capacity for intentionality and theory of mind, and for anticipating the consequences not only of human decisions, but also of its own “actions.” At the societal and ethical level (with reference to our co-existence with others and to what is good and bad for us) especially the latter capabilities (intentionality, theory of mind, and anticipation) could arguably help AI to better inform humans about potential negative impacts of its functioning and use on society, and to help avoid them while favouring positive impacts. Of course, on the negative side, as showed by human history, both intentionality and theory of mind may be used by the AI for negative purposes, for instance for favouring the AI’s own interests or the interests of the limited groups that control it. Human intentionality has not always favoured out-group individuals or species, or indeed the planet as a whole. This point connects to one of the most debated issues in AI ethics, the so-called AI alignment problem: how can we be sure that AI systems conform to human values? How can we make AI aligned with our own interests? And whose values and interests should we take as reference? Cultural diversity is an important and challenging factor to take into account in these reflections.

I think there is also a question that precedes that of AI value alignment: can AI really have values? In other words, is the capacity for evaluation that possibly drives the elaboration of values in AI the same as in humans? And is AI capable of evaluating its own values, including its ethical values, a reflective process that drives the self-critical elaboration of values in humans, making us evaluative subjects? In fact, the capacity for evaluation (which may be defined as the sensitivity to reward signals and the ability to discriminate between good and bad things in the world on the basis of specific needs, motivations, and goals) is a defining feature of biological organisms, namely of the brain. AI may be programmed to discriminate between what humans consider to be good and bad things in the world, and it is also conceivable that AI will be less dependent on humans in applying this distinction. However, this does not entail that it “evaluates” in the sense that it autonomously performs an evaluation and subjectively experiences its evaluation.

It is possible that an AI system may approximate the diversity of cognitive processes that the brain has access to, for instance the processing of various sensory modalities, while AI remains unable to incorporate the values attributed to the processed information and to its representation, as the human brain can do. In other words, to date AI remains devoid of any experiential content, and for this reason, for the time being, AI is different from the human brain because of its inability to attribute experiential value to information. This is the fundamental reason why present AI systems lack subjective experience. If we want to refer to needs (which are a prerequisite for the capacity for evaluation), current AI appears limited to epistemic needs, without access to, for example, moral and aesthetic needs. Therefore, the values that AI has at least so far been able to develop or be sensible to are limited to the epistemic level, while morality and aesthetics are beyond our present technological capabilities. I do not deny that overcoming this limitation may be a matter of further technological progress, but for the time being we should carefully consider this limitation in our reflections about whether it is wise to strive for conscious AI systems. If the form of consciousness that we can realistically aspire to engineer today is limited to the cognitive dimension, without any sensibility to ethical deliberation and aesthetic appreciation, I am afraid that the risk of misusing or exploiting it for selfish purposes is quite high.

One could object that an AI system limited to epistemic values is not really conscious (at least not in a fully human sense). However, the fact remains that its capacity to interact with the world to achieve the goals it has been programmed to achieve would be greatly enhanced if it had this cognitive form of consciousness. This increases our responsibility to hypothetically consider whether conscious AI, even if limited and much more rudimentary than human consciousness, may be for the better or for the worse.

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

Michele Farisco, Kathinka Evers, Jean-Pierre Changeux. Is artificial consciousness achievable? Lessons from the human brain. Neural Networks, Volume 180, 2024. https://doi.org/10.1016/j.neunet.2024.106714

We like challenging questions

Artificial consciousness and the need for epistemic humility

4 June, 2024 / / 2 Comments

As I wrote in previous posts on this blog, the discussion about the possibility of engineering an artificial form of consciousness is growing along with the impressive advances of artificial intelligence (AI). Indeed, there are many questions arising from the prospect of an artificial consciousness, including its conceivability and its possible ethical implications. We  deal with these kinds of questions as part of a EU multidisciplinary project, which aims to advance towards the development of artificial awareness.

Here I want to describe the kind of approach to the issue of artificial consciousness that I am inclined to consider the most promising. In a nutshell, the research strategy I propose to move forward in clarifying the empirical and theoretical issues of the feasibility and the conceivability of artificial consciousness, consists in starting from the form of consciousness we are familiar with (biological consciousness) and from its correlation with the organ that science has revealed is crucial for it (the brain).

In a recent paper, available as a pre-print, I analysed the question of the possibility of developing artificial consciousness from an evolutionary perspective, taking the evolution of the human brain and its relationship to consciousness as a benchmark. In other words, to avoid vague and abstract speculations about artificial consciousness, I believe it is necessary to consider the correlation between brain and consciousness that resulted from biological evolution, and use this correlation as a reference model for the technical attempts to engineer consciousness.

In fact, there are several structural and functional features of the human brain that appear to be key for reaching human-like complex conscious experience, which current AI is still limited in emulating or accounting for. Among these are:

  • massive biochemical and neuronal diversity
  • long period of epigenetic development, that is, changes in the brain’s connections that eventually change the number of neurons and their connections in the brain network as a result of the interaction with the external environment
  • embodied sensorimotor experience of the world
  • spontaneous brain activity, that is, an intrinsic ability to act which is independent of external stimulation
  • autopoiesis, that is, the capacity to constantly reproduce and maintain itself
  • emotion-based reward systems
  • clear distinction between conscious and non-conscious representations, and the consequent unitary and specific properties of conscious representations
  • semantic competence of the brain, expressed in the capacity for understanding
  • the principle of degeneracy, which means that the same neuronal networks may support different functions, leading to plasticity and creativity.

These are just some of the brain features that arguably play a key role for biological consciousness and that may inspire current research on artificial consciousness.

Note that I am not claiming that the way consciousness arises from the brain is in principle the only possible way for consciousness to exist: this would amount to a form of biological chauvinism or anthropocentric narcissism.  In fact, current AI is limited in its ability to emulate human consciousness. The reasons for these limitations are both intrinsic, that is, dependent on the structure and architecture of AI, and extrinsic, that is, dependent on the current stage of scientific and technological knowledge. Nevertheless, these limitations do not logically exclude that AI may achieve alternative forms of consciousness that are qualitatively different from human consciousness, and that these artificial forms of consciousness may be either more or less sophisticated, depending on the perspectives from which they are assessed.

In other words, we cannot exclude in advance that artificial systems are capable of achieving alien forms of consciousness, so different from ours that it may not even be appropriate to continue to call it consciousness, unless we clearly specify what is common and what is different in artificial and human consciousness. The problem is that we are limited in our language as well as in our thinking and imagination. We cannot avoid relying on what is within our epistemic horizon, but we should also avoid the fallacy of hasty generalization. Therefore, we should combine the need to start from the evolutionary correlation between brain and consciousness as a benchmark for artificial consciousness, with the need to remain humble and acknowledge the possibility that artificial consciousness may be of its own kind, beyond our view.

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

Approaching future issues

A way out of the Babylonian confusion of tongues in the theorizing of consciousness?

Dictionary "Collaborate", Image by Dianne Hope from Pixabay
16 April, 2024 / / 1 Comment

There is today a wide range of competing theories, each in its own way trying to account for consciousness in neurobiological terms. Parallel to the “Babylonian confusion of tongues” and inability to collaborate that this entails in the theorizing of consciousness, progress has been made in the empirical study of the brain. Advanced methods for imaging and measuring the brain and its activities map structures and functions that are possibly relevant for consciousness. The problem is that these empirical data once again inspire a wide range of theories about the place of consciousness in the brain.

It has been pointed out that a fragmented intellectual state such as this, where competing schools of thought advocate their own theories based on their own starting points – with no common framework or paradigm within which the proposals can be compared and assessed – is typical of a pre-scientific stage of a possibly nascent science. Given that the divergent theories each claim scientific status, this is of course troubling. But maybe the theories are not as divergent as they seem?

It has been suggested that several of the theories, upon closer analysis, possibly share certain fundamental ideas about consciousness, which could form the basis of a future unified theory. Today I want to recommend an article that self-critically examines this hope for a way out of the Babylonian confusion. If the pursuit of a unified theory of consciousness is not to degenerate into a kind of “manufactured uniformity,” we must first establish that the theories being integrated are indeed comparable in relevant respects. But can we identify such common denominators among the competing theories, which could support the development of an overarching framework for scientific research? That is the question that Kathinka Evers, Michele Farisco and Cyriel Pennartz investigate for some of the most debated neuroscientifically oriented theories of consciousness.

What do the authors conclude? Something surprising! They come to the conclusion that it is actually quite possible to identify a number of common denominators, which show patterns of similarities and differences among the theories, but that this is still not the way to an overall theory of consciousness that supports hypotheses that can be tested experimentally. Why? Partly because the common denominators, such as “information,” are sometimes too general to function as core concepts in research specifically about consciousness. Partly because theories that have common denominators can, after all, be conceptually very different.

The authors therefore suggest, as I understand them, that a more practicable approach could be to develop a common methodological approach to testing hypotheses about relationships between consciousness and the brain. It is perhaps only in the empirical workshop, open to the unexpected, so to speak, that a scientific framework, or paradigm, can possibly begin to take shape. Not by deliberately formulating unified theory based on the identification of common denominators among competing theories, which risks manufacturing a facade of uniformity.

The article is written in a philosophically open-minded spirit, without ties to specific theories. It can thereby stimulate the creative collaboration that has so far been inhibited by self-absorbed competition between schools of thought. Read the article here: Assessing the commensurability of theories of consciousness: On the usefulness of common denominators in differentiating, integrating and testing hypotheses.

I would like to conclude by mentioning an easily neglected aspect of how scientific paradigms work (according to Thomas Kuhn). A paradigm does not only generate possible explanations of phenomena. It also generates the problems that researchers try to solve within the paradigm. Quantum mechanics and evolutionary biology enabled new questions that made nature problematic in new explorable ways. A possible future paradigm for scientific consciousness research would, if this is correct, not answer the questions about consciousness that baffle us today (at least not without first reinterpreting them). Rather, it would create new, as yet unasked questions, which are explorable within the paradigm that generates them.

The authors of the article may therefore be right that the most fruitful thing at the moment is to ask probing questions that help us delineate what actually lends itself to investigation, rather than to start by manufacturing overall theoretical uniformity. The latter approach would possibly put the cart before the horse.

Pär Segerdahl

Written by…

Pär Segerdahl, Associate Professor at the Centre for Research Ethics & Bioethics and editor of the Ethics Blog.

K. Evers, M. Farisco, C.M.A. Pennartz, “Assessing the commensurability of theories of consciousness: On the usefulness of common denominators in differentiating, integrating and testing hypotheses,” Consciousness and Cognition, Volume 119, 2024,

This post in Swedish

Minding our language

A strategy for a balanced discussion of conscious AI

Image by Gerd Altman on Pixabay
9 April, 2024 / / 3 Comments

Science and technology advance so rapidly that it is hard to keep up with them. This is true not only for the general public, but also for the scientists themselves and for scholars from fields like ethics and regulation, who find it increasingly difficult to predict what will come next. Today AI is among the most advanced scientific endeavors, raising both significant expectations and more or less exaggerated worries. This is mainly due to the fact that AI is a concept so emotionally, socially, and politically charged as to make a balanced evaluation very difficult. It is even more so when capacities and features that are considered almost uniquely human, or at least shared with a limited number of other animals, are attributed to AI. This is the case with consciousness.

Recently, there has been a lively debate about the possibility of developing conscious AI. What are the reasons for this great interest? I think it has to do with the mentioned rapid advances in science and technology, as well as new intersections between different disciplines. Specifically, I think that three factors play an important role: the significant advancement in understanding the cerebral bases of conscious perception, the impressive achievements of AI technologies, and the increasing interaction between neuroscience and AI. The latter factor, in particular, resulted in so-called brain-inspired AI, a form of AI that is explicitly modeled on our brains.

This growing interest in conscious AI cannot ignore certain risks of varying relevance, including theoretical, practical, and ethical relevance. Theoretically, there is not a shared, overarching theory or definition of consciousness. Discussions about what consciousness is, what the criteria for a good scientific theory should be, and how to compare the various proposed theories of consciousness are still open and difficult to resolve.

Practically, the challenge is how to identify conscious systems. In other words, what are the indicators that reliably indicate whether a system, either biological or artificial, is conscious?

Finally, at the ethical level several issues arise. Here the discussion is very lively, with some calling for an international moratorium on all attempts to build artificial consciousness. This extreme position is motivated by the need for avoiding any form of suffering, including possibly undetectable artificial forms of suffering. Others question the very reason for working towards conscious AI: why should we open another, likely riskier box, when society cannot really handle the impact of AI, as illustrated by Large Language Models? For instance, chatbots like ChatGPT show an impressive capacity to interact with humans through natural language, which creates a strong feeling that these AI systems have features like consciousness, intentionality, and agency, among others. This attribution of human qualities to AI eventually impacts the way we think about it, including how much weight and value we give to the answers that these chatbots provide.

The two arguments above illustrate possible ethical concerns that can be raised against the development of conscious artificial systems. Yet are the concerns justified? In a recent chapter, I propose a change in the underlying approach to the issue of artificial consciousness. This is to avoid the risk of vague and not sufficiently multidimensional analyses. My point is that consciousness is not a unified, abstract entity, but rather like a prism, which includes different dimensions that could possibly have different levels. Based on a multidimensional view of consciousness, in a previous paper I contributed a list of indicators that are relevant also for identifying consciousness in artificial systems. In principle, it is possible that AI can manifest some dimensions of consciousness (for instance, those related to sophisticated cognitive tasks) while lacking others (for instance, those related to emotional or social tasks). In this way, the indicators provide not only a practical tool for identifying conscious systems, but also an ethical tool to make the discussion on possible conscious AI more balanced and realistic. The question whether some AI is conscious or not cannot be considered a yes/no question: there are several nuances that make the answer more complex.

Indeed, the indicators mentioned above are affected by a number of limitations, including the fact that they are developed for humans and animals, not specifically for AI. For this reason, research is still ongoing on how to adapt these indicators or possibly develop new indicators specific for AI. If you want to read more, you can find my chapter here: The ethical implications of indicators of consciousness in artificial systems.

Written by…

Michele Farisco, Postdoc Researcher at Centre for Research Ethics & Bioethics, working in the EU Flagship Human Brain Project.

Michele Farisco. The ethical implications of indicators of consciousness in artificial systems. Developments in Neuroethics and Bioethics. Available online 1 March 2024. https://doi.org/10.1016/bs.dnb.2024.02.009

We want solid foundations

« Older posts