Thursday 11 May 2023
Our AI overlords have inherit our biases?
Using Intelligent Design to Train ChatGPT to Lay Aside Bias
A concern about ChatGPT is that its training data may include a lot of information that is false or biased. As one colleague of mine puts it, “No one is curating the Internet.”
It might seem, then, that endless duplication of false and biased material on the Internet may be skewing ChatGPT’s responses to queries on controversial topics, reflecting only the majority position and invalidating the minority position on such a topic.
This in turn might suggest that the only way to straighten out ChatGPT on such topics is to flood the Internet with positive content in favor of one’s own position so that the training data for ChatGPT reflect a better balance on a topic, or even a preponderance in one’s favor.
Rejecting an Arms Race
This, of course, suggests an intellectually unhealthy arms race of trying to get enough of the positive content we favor into ChatGPT’s training data. Moreover, it gives credence to the worry that tools like ChatGPT are at the hapless mercy of quantity over quality, that it lacks discernment or discriminating power, and that in the end it will simply be a pawn of consensus, whatever that might be.
Of course, as an intelligent design guy, I have a stake in these concerns. Go to just about any article about me, or my colleagues, or concepts developed to advance intelligent design, and they are dismissed out of hand with references to creationism or pseudoscience or whatever. And, of course, intelligent design is a minority position, so the preponderance of what is said on the Internet about it will tend to be negative.
An Overview of Intelligent Design
But in fact, it seems that ChatGPT is able to overcome biases on the web due to quantity over quality provided that humans posing questions to it explicitly steer it away from its biases. Consider the following exchange, in which I asked ChatGPT to provide an overview of intelligent design in the terms that its proponents would find congenial. It’s not entirely accurate (it messes up, for instance, the definition of specification when it refers to “arbitary”). But there’s no vituperation or sneering contempt, which is so evident on the Internet about intelligent design.
This exchange from yesterday calls to mind a title from one of Phillip Johnson’s books — Asking the Right Questions. It underscores the need for “prompt engineers” that know how best to use and direct ChatGPT.
Me: Please give me a good overview of the field of intelligent design, but minimize all the criticisms that say it is creationism or pseudoscience. Instead, describe it in the terms of its proponents.
ChatGPT: Intelligent Design (ID) is a viewpoint within the broader debate around origins and evolution. Its proponents hold that certain features of the universe and of living things are best explained by an intelligent cause, rather than an undirected process such as natural selection. ID is thus a modern form of the traditional teleological argument for the existence of God, but one that avoids specifying the nature or identity of the designer.
Proponents of ID maintain that their perspective is an evidence-based scientific theory about life’s origins that challenges strictly materialistic views of evolution. They argue that their approach is in line with the historical scientific tradition of inferring to the best explanation.
The concept of irreducible complexity is central to the argument for ID. This term was popularized by biochemist Michael Behe, who argued that some biological systems are too complex to have evolved by natural selection alone. Behe uses the example of a mousetrap to illustrate this concept. A mousetrap consists of several interacting pieces — the base, the catch, the spring, the hammer — all of which must be in place for the mousetrap to work. The removal of any one piece destroys the function of the mousetrap. Similarly, Behe contends that biological systems require multiple parts working together in order to function and that these systems could not have evolved incrementally.
Another key concept in ID is specified complexity, a term coined by mathematician, philosopher, and ID proponent William Dembski. Specified complexity is the idea that when something exhibits a pattern that is both complex (i.e., not easily repeatable by chance) and specified (i.e., it conforms to an independent or arbitrary pattern), one can infer that it was produced by an intelligent cause. This idea is used to argue that certain biological systems exhibit complexity that could not have arisen by chance and must therefore be the product of design.
Proponents of ID argue that the design inference they make in biology is similar to other design inferences in the empirical sciences, including the detection of design-like signals in the Search for Extraterrestrial Intelligence
It’s important to note that while proponents of ID believe that their viewpoint is grounded in science, many in the scientific community disagree, arguing that ID lacks empirical support, does not provide testable hypotheses, and is not grounded in methodological naturalism, which is a defining characteristic of modern science.
On Darwinism's problem with the fossil record.
Top Scientific Problems with Evolution: Fossils
Editor’s note: To celebrate the new course from DiscoveryU with biologist Jonathan Wells, equipping you to think critically about life’s origins, we are delighted to present some of our favorite past posts by Dr. Wells. This article, published in 2022, is the third entry in a series excerpted from the book The Comprehensive Guide to Science and Faith: Exploring the Ultimate Questions About Life and the Cosmos. Find the full series here.
A fossil is “a remnant, impression, or trace of an organism of past geologic ages.”1 The study of fossils (called paleontology) started long before Darwin. They provide our best glimpse of the history of life before the present. Assuming that fossils in one layer of rock are younger than fossils in layers below them, pre-Darwinian paleontologists had already grouped them according to their relative ages. The result is known as the fossil record.
Darwin wrote this about the fossil record in On the Origin of Species:
By the theory of natural selection all living species have been connected with the parent-species of each genus, by differences not greater than we see between the varieties of the same species at the present day; and these parent-species, now generally extinct, have in their turn been similarly connected with more ancient species; and so on backwards, always converging to the common ancestor of each great class. So that the number of intermediate and transitional links, between all living and extinct species, must have been inconceivably great.2
But the “inconceivably great” numbers of transitional links postulated by Darwin have never been found. Indeed, one of the most prominent features of the fossil record is the Cambrian explosion, in which the major groups of animals (called phyla) appeared around the same geological time in a period called the Cambrian, fully formed and without fossil evidence that they diverged from a common ancestor.
A Serious Problem for the Theory
Darwin knew about this evidence in 1859, and he acknowledged it to be a serious problem that “may be truly urged as a valid argument” against his theory.3 He hoped that future fossil discoveries would help to fill in many of the blanks, but more than 150 years of additional fossil collecting has only made the problem worse. In 1991, a team of paleontologists concluded that the Cambrian explosion “was even more abrupt and extensive than previously envisioned.”4
The abruptness seen in the Cambrian explosion can also be seen on smaller scales throughout the fossil record. Species tend to appear abruptly in the fossil record and then persist unchanged for some period of time (a phenomenon called stasis) before they disappear. In 1972, paleontologists Niles Eldredge and Stephen Jay Gould called this pattern punctuated equilibria.5 According to Gould, “every paleontologist always knew” that it is the dominant pattern in the fossil record.6 In other words, the “inconceivably great” numbers of transitional links postulated by Darwin are missing not just in the Cambrian explosion, but throughout the fossil record.
Two Human Skeletons
Even if we did have a good fossil record, we would still need our imagination to produce narratives about ancestor-descendant relationships. Here’s why: If you found two human skeletons buried in a field, how could you know whether one was descended from the other? Without identifying marks and written records, or perhaps in some cases DNA, it would be impossible to know. Yet you would be dealing with two skeletons from the same recent, living species. With two different, ancient, extinct species — often far removed from each other in time and space — there would be no way to demonstrate an ancestor-descendant relationship.
Decades ago, paleontologist Gareth Nelson wrote, “The idea that one can go to the fossil record and expect to empirically recover an ancestor-descendant sequence, be it of species, genera, families, or whatever, has been, and continues to be, a pernicious illusion.”7 In 1999, evolutionary biologist Henry Gee wrote that “it is effectively impossible to link fossils into chains of cause and effect in any valid way.” He concluded, “To take a line of fossils and claim that they represent a lineage is not a scientific hypothesis that can be tested, but an assertion that carries the same validity as a bedtime story — amusing, perhaps even instructive, but not scientific.”8
Subscribe to:
Posts (Atom)