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?
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
We like challenging questions
Dear Dr. Evers,
I am the author of that (meanwhile rather old but unpublished) paper titled “Conscious Machines” which you may have seen in the course of your research, and as a comment on your present article perhaps this: In my article I claim that we have conscious machines since decades, but have (so far) not being widely aware of the fact because philosophers and engineers are using different languages (i.e. contributing their ideas in different ways/habits of formulating thoughts and suggestions). The example of a conscious machine which I was presenting in my paper is the Aegis system of the US Navy, which is meanwhile part of the standard equipment of the Navy’s destroyers. That I was using just a military system as my example was due to the idea that consciousness is an important tool of survival while just military systems have very much the job of having to survive in a very hostile environment. Military systems, though, are not only expected to survive but can very well also be constructed for the job of attacking and killing (and be it by “suicide” as in the case of a kamikaze drone). From details in reports which occasionally came via the internet I was already a few years ago concluding that Israel has already tested drones which kill without human supervision in Gaza, and anyway it is simply to be expected that this line of development in military technology will be pursued, then marketed, sold and at least occasionally be used (one should pay attention to news especially from the Middle East and also Ukraine). In this sense, the spirit is already out of the bottle. This deplorable fact should, though, not hinder us from looking for better possible uses for AI, and there I should, e.g., strongly recommend that computers should be fed with all valid laws and be enabled to follow court procedures in order to produce “suggested decisions” parallel to human judges, because what we have, e.g., rather recently seen of court decisions in the USA (and years ago also in Finland) is “not very satisfactory” (and often in obvious need of correction by some impartial expert). And similar things can be said about the possibility of AI as an advisor in diplomatic matters: human diplomats may be aware of (and unluckily also be subject to) the innate primate programs which tend to be aroused during confrontations (and which are anyway intensely “cultivated” by profit-oriented media), so that also here the “opinions of an impartial AI-agent” might be of some help. – More in general I was in my paper on page 23, about “zombies”, formulating some idea what one could reasonably expect from AI (and what perhaps not). I am quoting there some Moody (1994) who points out “that zombies who grew up in our midst might become glib in the use of our language, including our philosophical talk about consciousness and dreams …”, which in turn reminded me of situations in social gatherings where the participants heatedly exchange “politically correct” formulations about topics which the exchangers do in fact not know a thing about, such as, say, psychoanalysis. For the possibilities of AI this would mean that even a computer which has been fed with MASSES of information may STILL be unable to react/reply in ways which presuppose own/personal experience with impressions which come via several (or even ALL) of our sensory systems.
Thanks for your interesting comment! /Pär