ChatGPT Heralds an Intellectual Revolution
By Henry Kissinger, Eric Schmidt And Daniel Huttenlocher
Anew technology bids to transform the human cognitive process as
it has not been shaken up since the invention of printing. The technology that
printed the Gutenberg Bible in 1455 made abstract human thought communicable
generally and rapidly. But new technology today reverses that process. Whereas
the printing press caused a profusion of modern human thought, the new
technology achieves its distillation and elaboration. In the process, it
creates a gap between human knowledge and human understanding. If we are to
navigate this transformation successfully, new concepts of human thought and
interaction with machines will need to be developed. This is the essential
challenge of the Age of Artificial Intelligence.
The new technology is known as generative artificial intelligence;
GPT stands for Generative Pre-Trained Transformer. ChatGPT, developed at the
OpenAI research laboratory, is now able to converse with humans. As its
capacities become broader, they will redefine human knowledge, accelerate
changes in the fabric of our reality, and reorganize politics and society.
Generative artificial intelligence presents a philosophical and practical
challenge on a scale not experienced since the beginning of the Enlightenment.
The printing press enabled scholars to replicate each other’s findings quickly
and share them. An unprecedented consolidation and spread of information
generated the scientific method.
What had been impenetrable became the starting point of
accelerating query. The medieval interpretation of the world based on religious
faith was progressively undermined. The depths of the universe could be
explored until new limits of human understanding were reached.
Generative AI will similarly open revolutionary avenues for human
reason and new horizons for consolidated knowledge. But there are categorical
differences. Enlightenment knowledge was achieved progressively, step by step,
with each step testable and teachable. AI-enabled systems start at the other
end. They can store and distill a huge amount of existing information, in
ChatGPT’s case much of the textual material on the internet and a large number
of books—billions of items. Holding that volume of information and distilling
it is beyond human capacity.
Sophisticated AI methods produce results without explaining why or
how their process works.
The GPT computer is prompted by a query from a human. The learning
machine answers in literate text within seconds. It is able to do so because it
has pregenerated representations of the vast data on which it was trained.
Because the process by which it created those representations was developed by
machine learning that reflects patterns and connections across vast amounts of
text, the precise sources and reasons for any one representation’s particular
features remain unknown. By what process the learning machine stores its
knowledge, distills it and retrieves it remains similarly unknown.
Whether that process will ever be discovered, the mystery
associated with machine learning will challenge human cognition for the
indefinite future.
AI’s capacities are not static but expand exponentially as the
technology advances. Recently, the complexity of AI models has been doubling
every few months. There-fore generative AI systems have capabilities that
remain undisclosed even to their inventors. With each new AI system, they are
building new capacities without understanding their origin or destination. As a
result, our future now holds an entirely novel element of mystery, risk and
surprise.
Enlightenment science accumulated certainties; the new AI
generates cumulative ambiguities. Enlightenment science evolved by making
mysteries explicable, delineating the boundaries of human knowledge and
understanding as they moved. The two faculties moved in tandem: Hypothesis was
understanding ready to become knowledge; induction was knowledge turning into
understanding. In the Age of AI, riddles are solved by processes that remain
unknown.
This disorienting paradox makes mysteries unmysterious but also
unexplainable. Inherently, highly complex AI furthers human knowledge but not
human understanding— a phenomenon contrary to almost all of postEnlightenment
modernity. Yet at the same time AI, when coupled with human reason, stands to
be a more powerful means of discovery than human reason alone.
The essential difference between the Age of Enlightenment and the
Age of AI is thus not technological but cognitive. After the Enlightenment,
philosophy accompanied science. Bewildering new data and often counterintuitive
conclusions, doubts and insecurities were allayed by comprehensive explanations
of the human experience.
Generative AI is similarly poised to generate a new form of human
consciousness. As yet, however, the opportunity exists in colors for which we
have no spectrum and in directions for which we have no compass. No political
or philosophical leadership has formed to explain and guide this novel
relationship between man and machine, leaving society relatively unmoored.
ChatGPT is an example of what is known as a large language model,
which can be used to generate humanlike text. GPT is a type of model that can
be automatically learned from large amounts of text without the need for human
supervision. ChatGPT’s developers have fed it a massive amount of the textual
content of the digital world.
Computing power allows the model to capture patterns and
connections.
The ability of large language models to generate humanlike text
was an almost accidental discovery. These models are trained to be able to
predict the next word in a sentence, which is useful in tasks such as
autocompletion for sending text messages or searching the web. But it turns out
that the models also have the unexpected ability to create highly articulate
paragraphs, articles and in time perhaps books.
ChatGPT is further specialized beyond a basic large language
model, using feedback from humans to tune the model so that it generates more
natural-seeming conversational text, as well as to try to contain its
propensity for inappropriate responses (a substantial challenge for large
language models). ChatGPT instantaneously converts its representations into
unique responses. The ultimate impression on a human conversant is that the AI
is relating stationary collections of facts into dynamic concepts.
ChatGPT’s answers, statements and observations appear without an
explanation of where they came from and without an identifiable author. On its
face, ChatGPT has no discernible motive or bias. Its outputs are complex, but
its work is astonishingly rapid: In a matter of seconds, it can produce answers
that coherently explain a high-level topic. They are not simply copied from the
text in the computer’s memory. They are generated anew by a process that humans
are unable to replicate. It is able to incorporate hypotheticals and nonobvious
psychological inferences. It can prioritize among billions of data points to
select the single set of 200 words that is most relevant (or will appear most
relevant to a human reader). In its own words, it makes probabilistic judgments
about future outcomes, blending information from discrete domains into an
integrated answer. It appears to accept contrary views, presenting them as
simultaneously compatible. It imitates other writing without copying it. Even
though the model is incapable of understanding in the human sense, its outputs
reflect an underlying essence of human language.
We asked ChatGPT to explain its own capabilities. Can it predict
the future?
No, it responded. “I can only provide information and answer
questions based on the data that I have been trained on. I do not have personal
experiences or consciousness, so I am not able to make predictions or forecasts
about future events.”
Is it able to make probabilistic judgments?
“I can provide probabilistic judgments based on the data that I
have been trained on. For example, if I have been trained on a large dataset of
weather patterns, I might be able to provide a probabilistic judgment about the
likelihood of a particular type of weather occurring in a specific location on
a given day. However, it is important to note that these probabilistic
judgments are based on patterns and trends in the data, and they may not always
accurately reflect
Prompt: Write a short essay in the thought of Henry Kissinger
about the role of artificial general intelligence in international arms
control.
The response began: “As we stand on the cusp of a new
technological revolution, the question of artificial general intelligence and
its role in international arms control becomes increasingly pressing. Will AGI
bring about unprecedented stability, as advanced systems take over the decision-making
processes associated with nuclear deterrence? Or will it introduce a new set of
dangers, as the global balance of power is altered by the development of highly
intelligent machines?” We queried ChatGPT on topics of immediate interest, such
as Russia’s role in maintaining or undermining European stability. It gave
seemingly thoughtful, concise answers in less than a minute, balancing
contradictory information and answering fully without appearing to have an
opinion. On the receiving end, generative artificial intelligence appears
superhuman or at least greatly enhanced cognitively. To the naive user, it
seems like a supremely fast and highly articulate librarian-scholar coupled
with a professorial savant. It facilitates the summary and interrogation of the
world’s knowledge far more effectively than any existing technological or human
interface, and it does so with unique comprehensiveness. Its ability to
integrate multiple knowledge domains and imitate multiple aspects of human
thought makes it polymathic to a degree that exceeds the ambitions of any group
of top-level humans. All of these qualities encourage unquestioning acceptance
of whatever GPT generates and a kind of magical atmosphere for their operation.
Yet at the same time, it possesses a capability to misinform its human users
with incorrect statements and outright fabrications Within a few days of
ChatGPT’s launch, more than a million people signed up to ask it questions.
Hundreds of companies are working on generative technologies, and investment is
pouring in, tilting discoveries to the commercial field. The huge commercial
motives will, for the foreseeable future, take precedence over long-range
thinking about their implications. The biggest of these models are expensive to
train—north of $1 billion per model. Once trained, thousands of computers work
24 hours a day to operate them. Operating a pretrained model is cheap compared
with the training itself, and it requires only capital, rather than capital and
computing skill. Still, paying for exclusive use of a large language model
remains outside the bounds of most enterprises. These models’ developers are
likely to sell subscriptions, so that a single model will serve the needs of
many thousands of individuals and businesses. As a result, the number of very
large language models in the next decade may be relatively constrained. Design
and control of these models will be highly concentrated, even as their power to
amplify human efforts and thought becomes much more diffuse. Generative AI will
be used beyond the large language model to build many types of models, and the
method will become increasingly multimodal and arcane. It will alter many
fields of human endeavor, for example education and biology. Different models
will vary in their strengths and weaknesses. Their capabilities—from writing
jokes and drawing paintings to designing antibodies—will likely continue to
surprise us. Just as the large language model developed a richer model of human
language than its creators anticipated, generative AIs in many fields are
likely to learn more than their assigned tasks imply. Breakthroughs in
traditional scientific problems have become probable. The long-term importance
of generative AI transcends commercial implications or even noncommercial scientific
breakthroughs. It is not only generating answers; it is generating
philosophically profound questions. It will infuse diplomacy and security
strategy. Yet none of the creators of this technology are addressing the
problems it will itself create. Nor has the U.S. government addressed the
fundamental changes and transformations that loom. The seeming perfection of
the model’s answers will produce overconfidence in its results. This is already
an issue, known as “automation bias,” with far less sophisticated computer
programs. The effect is likely to be especially strong where the AI generates
authoritative- sounding text. ChatGPT is likely to reinforce existing
predispositions toward reliance on automated systems reducing the human element.
The lack of citations in Chat-GPT’s answers makes it difficult to
discern truth from misinformation.
We know already that malicious actors are injecting reams of
manufactured “facts,” and increasingly convincing deepfake images and videos,
into the internet—that is to say, into ChatGPT’s present and future learning
set. Because ChatGPT is designed to answer questions, it sometimes makes up
facts to provide a seemingly coherent answer.
That phenomenon is known among AI researchers as “ hallucination”
or “stochastic parroting,” in which an AI strings together phrases that look
real to a human reader but have no basis in fact. What triggers these errors
and how to control them remain to be discovered.
We asked ChatGPT to give “six references on Henry Kissinger’s
thoughts on technology.” It generated a list of articles purportedly by Mr.
Kissinger. All were plausible topics and outlets, and one was a real title
(though its date was wrong). The rest were convincing fabrications.
Possibly the so-called titles appear as isolated sentences in the
vastness of GPT’s “facts,” which we are not yet in a position to discover.
ChatGPT has no immediately evident personality, although users
have occasionally prompted it to act like its evil twin. ChatGPT’s lack of an
identifiable author makes it harder for humans to intuit its leanings than it
would be to judge the political or social viewpoint of a human being. Because
the machine’s design and the questions fed to it generally have a human origin,
however, we will be predisposed to imagine humanlike reasoning. In reality, the
AI is engaging in an inhuman analog to cognition. Though we perceive generative
AI in human terms, its mistakes are not the mistakes of a human; it makes the
mistakes of a different form of intelligence based on pattern recognition.
Humans should not identify these mistakes as errors. Will we be able to recognize
its biases and flaws for what they are? Can we develop an interrogatory mode
capable of questioning the veracity and limitations of a model’s answers, even
when we do not know the answers ahead of time?
Thus, AI’s outputs remain difficult to explain. The truth of
Enlightenment science was trusted because each step of replicable experimental
processes was also tested, hence trusted. The truth of generative AI will need
to be justified by entirely different methods, and it may never become similarly
absolute. As we attempt to catch our understanding up to our knowledge, we will
have to ask continuously: What about the machine has not yet been revealed to
us? What obscure knowledge is it hiding?
Generative AI’s reasoning is likely to change over time, to some
extent as part of the model’s training. It will become an accelerated version
of traditional scientific progress, adding random adaptations to the very
process of discovery. The same question put to Chat-GPT over a period of time
may yield
changed answers. Slight differences in phrasing that seem
unimportant at the first pass may cause drastically different results when
repeated. At the present, ChatGPT is learning from an information base that
ends at a fixed point in time. Soon, its developers will likely enable it to
take in new inputs, eventually consuming an unending influx of real-time
information. If investment continues to surge, the model is likely to be
retrained with rising frequency. That will increase its currency and accuracy
but will oblige its users to allow an everexpanding margin for rapid change.
Learning from the changing outputs of generative AI, rather than exclusively
from human written text, may distort today’s conventional human knowledge.
Even if generative AI models become fully interpretable and
accurate, they would still pose challenges inherent in human conduct. Students
are using ChatGPT to cheat on exams. Generative AI could create email
advertisements that flood in-boxes and are indistinguishable from the messages
of personal friends or business acquaintances. AI-generated videos and
advertisements depicting false campaign platforms could make it difficult to
distinguish between political positions. Sophisticated signals of
falsehood—including watermarks that signify the presence of AI-generated
content, which OpenAI is considering— may not be enough; they need to be
buttressed by elevated human skepticism.
Some consequences could be inherent. To the extent that we use our
brains less and our machines more, humans may lose some abilities. Our own
critical thinking, writing and (in the context of text-to-image programs like
Dall-E and Stability.AI) design abilities may atrophy. The impact of generative
AI on education could show up in the decline of future leaders’ ability to
discriminate between what they intuit and what they absorb mechanically. Or it
could result in leaders who learn their negotiation methods with machines and
their military strategy with evolutions of generative AI rather than humans at
the terminals of computers.
It is important that humans develop the confidence and ability to
challenge the outputs of AI systems. Doctors worry that deep-learning models
used to assess medical imaging for diagnostic purposes, among other tasks, may
replace their function. At what point will doctors no longer feel comfortable
questioning the answers their software gives them? As machines climb the ladder
of human capabilities, from pattern recognition to rational synthesis to
multidimensional thinking, they may begin to compete with human functions in
state administration, law and business tactics. Eventually, something akin to
strategy may emerge. How might humans engage with AI without abdicating
essential parts of strategy to machines? With such changes, what becomes of
accepted doctrines?
It is urgent that we develop a sophisticated dialectic that
empowers people to challenge the interactivity of generative AI, not merely to
justify or explain AI’s answers but to interrogate them. With concerted
skepticism, we should learn to probe the AI methodically and assess whether and
to what degree its answers are worthy of confidence. This will require
conscious mitigation of our unconscious biases, rigorous training and copious
practice.
The question remains: Can we learn, quickly enough, to challenge
rather than obey? Or will we in the end be obliged to submit? Are what we
consider mistakes part of the deliberate design? What if an element of malice
emerges in the AI?
Another key task is to reflect on which questions must be reserved
for human thought and which may be risked on automated systems. Yet even with
the development of enhanced skepticism and interrogatory skill, ChatGPT proves
that the genie of generative technology is out of the bottle. We must be
thoughtful in what we ask it.
Computers are needed to harness growing volumes of data. But
cognitive limitations may keep humans from uncovering truths buried in the
world’s information. ChatGPT possesses a capacity for analysis that is
qualitatively different from that of the human mind. The future therefore
implies a collaboration not only with a different kind of technical entity but
with a different kind of reasoning— which may be rational without being
reasonable, trustworthy in one sense but not in another. That dependency itself
is likely to precipitate a transformation in metacognition and hermeneutics—
the understanding of understanding— and in human perceptions of our role and
function.
Machine-learning systems have already exceeded any one human’s
knowledge. In limited cases, they have exceeded humanity’s knowledge,
transcending the bounds of what we have considered knowable. That has sparked a
revolution in the fields where such breakthroughs have been made. AI has been a
game changer in the core problem in biology of determining the structure of
proteins and in which advanced mathematicians do proofs, among many others.
As models turn from human-generated text to more inclusive inputs,
machines are likely to alter the fabric of reality itself. Quantum theory
posits that observation creates reality. Prior to measurement, no state is
fixed, and nothing can be said to exist. If that is true, and if machine
observations can fix reality as well— and given that AI systems’ observations
come with superhuman rapidity—the speed of the evolution of defining reality
seems likely to accelerate. The dependence on machines will determine and
thereby alter the fabric of reality, producing a new future that we do not yet
understand and for the exploration and leadership of which we must prepare.
Using the new form of intelligence will entail some degree of
acceptance of its effects on our self-perception, perception of reality and
reality itself. How to define and determine this will need to be addressed in
every conceivable context. Some specialties may prefer to muddle through with
the mind of man alone—though this will require a degree of abnegation without
historical precedent and will be complicated by competitiveness within and
between societies.
As the technology becomes more widely understood, it will have a
profound impact on international relations. Unless the technology for knowledge
is universally shared, imperialism could focus on acquiring and monopolizing
data to attain the latest advances in AI. Models may produce different outcomes
depending on the data assembled. Differential evolutions of societies may
evolve on the basis of increasingly divergent knowledge bases and hence of the
perception of challenges.
Heretofore most reflection on these issues has assumed congruence
between human purposes and machine strategies. But what if this is not how the
interaction between humanity and generative AI will develop? What if one side
considers the purposes of the other malicious?
The arrival of an unknowable and apparently omniscient instrument,
capable of altering reality, may trigger a resurgence in mystic religiosity.
The potential for group obedience to an authority whose reasoning is largely
inaccessible to its subjects has been seen from time to time in the history of
man, perhaps most dramatically and recently in the 20th-century subjugation of
whole masses of humanity under the slogan of ideologies on both sides of the
political spectrum. A third way of knowing the world may emerge, one that is
neither human reason nor faith. What becomes of democracy in such a world?
Leadership is likely to concentrate in hands of the fewer people
and institutions who control access to the limited number of machines capable
of high-quality synthesis of reality. Because of the enormous cost of their
processing power, the most effective machines within society may stay in the
hands of a small subgroup domestically and in the control of a few superpowers
internationally. After the transitional stage, older models will grow cheaper,
and a diffusion of power through society and among states may commence.
A reinvigorated moral and strategic leadership will be essential.
With-out guiding principles, humanity runs the risk of domination or anarchy,
unconstrained authority or nihilistic freedom. The need for relating major
societal change to ethical justifications and novel visions for the future will
appear in a new form. If the maxims put forth by ChatGPT are not translated
into a cognizably human endeavor, alienation of society and even revolution may
become likely.
Without proper moral and intellectual underpinnings, machines used
in governance could control rather than amplify our humanity and trap us
forever. In such a world, artificial intelligence might amplify human freedom
and transcend unconstrained challenges.
This imposes certain necessities for mastering our imminent
future. Trust in AI requires improvement across multiple levels of reliability—
in the accuracy and safety of the machine, alignment of AI aims with human
goals and in the accountability of the humans who govern the machine. But even
as AI systems grow technically more trustworthy, humans will still need to find
new, simple and accessible ways of comprehending and, critically, challenging
the structures, processes and outputs of AI systems.
Parameters for AI’s responsible use need to be established, with
variation based on the type of technology and the context of deployment.
Language models like ChatGPT demand limits on its conclusions. Chat-GPT needs
to know and convey what it doesn’t know and can’t convey.
Humans will have to learn new restraint. Problems we pose to an AI
system need to be understood at a responsible level of generality and
conclusiveness. Strong cultural norms, rather than legal enforcement, will be
necessary to contain our societal reliance on machines as arbiters of reality.
We will reassert our humanity by ensuring that machines remain objects.
Education in particular will need to adapt. A dialectical pedagogy
that uses generative AI may enable speedier and more-individualized learning
than has been possible in the past. Teachers should teach new skills, including
responsible modes of human-machine interlocution. Fundamentally, our
educational and professional systems must preserve a vision of humans as moral,
psychological and strategic creatures uniquely capable of rendering holistic
judgments.
Machines will evolve far faster than our genes will, causing
domestic dislocation and international divergence. We must respond with
commensurate alacrity, particularly in philosophy and conceptualism, nationally
and globally. Global harmonization will need to emerge either by perception or
by catastrophe, as Immanuel Kant predicted three centuries ago
We must include one caveat to this prediction: What happens if
this technology cannot be completely controlled? What if there will always be
ways to generate falsehoods, false pictures and fake videos, and people will
never learn to disbelieve what they see and hear? Humans are taught from birth
to believe what we see and hear, and that may well no longer be true as a
result of generative AI. Even if the big platforms, by custom and regulation,
work hard to mark and sort bad content, we know that content once seen cannot
be unseen. The ability to manage and control global distributed content fully
is a serious and unsolved problem.
The answers that ChatGPT gives to these issues are evocative only
in the sense that they raise more questions than conclusions. For now, we have
a novel and spectacular achievement that stands as a glory to the human mind as
AI. We have not yet evolved a destination for it. As we become Homo technicus, we hold an imperative to
define the purpose of our species. It is up to us to provide the real answers.
Mr. Kissinger served as secretary of state, 1973-77, and White
House national security adviser, 1969-75. Mr. Schmidt was CEO of Google,
2001-11 and executive chairman of Google and its successor, Alphabet Inc.,
2011-17. Mr. Huttenlocher is dean of the Schwarzman College of Computing at the
Massachusetts Institute of Technology. They are authors of “The Age of AI: And
Our Human Future.” The authors thank Eleanor Runde for her research.
Generative artificial intelligence presents a philosophical and
practical challenge on a scale not experienced since the start of the
Enlightenment.
Can we learn, quickly enough, to challenge rather than obey? Or
will we be obliged to submit? A third way of knowing the world may emerge, one
that is neither human reason nor faith.
