We should prepare to welcome our AI overlords?

 

Quantum technology?

 

The fossil record sides with devolution?

 Fossil Friday: New Study Confirms “Feathered Dinosaurs” Were Secondarily Flightless Birds

Günter Bechly

This Fossil Friday features one of the most well-known fossils of all, the famous Berlin specimen of the ancient bird Archaeopteryx from the Late Jurassic Solnhofen lithographic limestone in Bavaria. This iconic fossil was often considered to be a missing link between dinosaurs and birds, and thus a poster-child for fossil evidence in favor of Darwinian evolution.

In several past articles at Evolution News I have discussed the work of paleo-ornithologist Alan Feduccia, who courageously challenged the current consensus view that birds evolved from dinosaurs, as first suggested by Yale paleontologist John Ostrom in the mid 1970s with his Birds-are-Maniraptoran-Theropods (BMT) hypothesis. Feduccia elaborated his opposing views in numerous technical articles and four popular books titled “The Age of Birds“ (Feduccia 1980), “The Origin and Evolution of Birds” (Feduccia 1996), “Riddle of the Feathered Dragons” (Feduccia 2012), and most recently “Romancing the Birds and Dinosaurs” (Feduccia 2020). In a highly recommended review of the latter book, James (2021) wrote that “Every school child knows that birds are dinosaurs. Numerous magazine articles and popular books on the topic are available,” which is a remarkable success of selling a relatively recent scientific hypothesis to a wide general audience as an established fact. James continues that “in spite of all this confidence that the problem of the origin of birds has been solved, strong grounds exist for regarding the issue as unsettled, … Surely, admitting that the hypothesis that birds are maniraptoran theropods has serious problems would be better than to defend it so strongly.”

Three General Objections

In a review of Feduccia’s earlier book on the “Riddle of the Feathered Dragons,” Leigh (2014) listed three general objections by Feduccia to Ostrom’s dinosaur-to-bird hypothesis:

1.Most of the fossils used to support the theropod ancestry of birds are 20 million or more years younger than Archaeopteryx [this was famously labeled by Feduccia as a “temporal paradox”].

2.Theropod dinosaurs, Deinonychus included, were runners. It is much more reasonable to believe that, like bats and pterosaurs, birds descended from arboreal animals that evolved flight via the ability to glide.

3.The fossil record suggests that feathers evolved in connection with gliding and flying, rather than as insulation, or as part of an apparatus for catching insects, as Ostrom had suggested.

James (2021) listed several further problems that Feduccia has identified in his most recent book, which support his alternative view:

Neoflightless problem: Some flying and flightless birds are being misclassified as theropods.

Data analysis problem: Standard phylogenetic analyses are unable to detect complex evolutionary processes like convergence. Flightless birds converge on the body plan of theropods. To estimate basic similarities (homologies), anatomical studies are needed before the phylogenetic analysis.

Reduced forelimb problem: Complex characters, once lost, are unlikely to reevolve. Dollo’s Principle.

Protofeather problem: “Protofeathers” may be degraded collagen fibers.

Digit problem: The frame shift is a verificationist explanation, designed to fit the BMT.

Behavior problem: Studies that infer bird-like behavior in dinosaurs are about misidentified birds.

Confirmation problem: Scansoriopterygids have no distinctive theropod characters. An assumption that they are theropods is a form of confirmation bias. 

Geist (2022) commented in his review of the same book:

Feduccia leads readers through case after case where scientists, to accommodate the cladograms supporting the BMT hypothesis, have gone to extraordinary lengths to work around data that directly contradict their conclusions. Such efforts violate another bedrock, though not ironclad, philosophy of science: Occam’s Razor, stating that given multiple hypotheses, the simplest of competing theories be preferred over the more complex. Feduccia elegantly illustrates cases where conclusions drawn from cladistic analysis that dictate the connection between birds and dinosaurs violate this principle. At the very least this book might convince supporters of BMT to reevaluate the data.

This failure of cladistics was admitted by John Ostrom (1994: 172) himself, who commented that “reasoning of such dubious quality demonstrates a fundamental flaw in cladistic methodology. Preoccupation with compilation of lengthy lists of shared derived characteristics at the expense of a well-reasoned analysis will result in an erroneous phylogeny every time.”

Responding to Feduccia

So, how did the proponents of the dinosaurian ancestry of birds respond to Feduccia’s profound challenges? They did as Darwinists always do when their pet hypotheses are challenged with actual data: they ridicule and marginalize the critique or reduce it to a straw-man caricature. Here is what Ruben (1997) wrote in his review of Feduccia’s second book:

Specialists who are concerned with avian origins, especially those advocating a dinosaur-bird lineage, will be forced to confront a variety of previously ignored data that argue against this lineage. Thus, it hardly comes as a surprise that the book has been dismissed in recent reviews by several particularly zealous, cladistically oriented paleontologists. However, readers should not be misled by such shenanigans.

Zealous shenanigans? This is quite revealing for an alleged unbiased quest for scientific truth.

The Neoflightless Hypothesis

But, how does Feduccia explain the indisputable great similarity between vane-feathered bipedal dinosaurs (called Pennaraptora) and true birds? Actually, he does not dispute a close relationship at all, but suggests that Pennaraptora were not theropod dinosaurs but rather secondarily flightless birds, which he called the neoflightless hypothesis. Incidentally, the same claim has been made by skeptics of Darwinian evolution.

Now, a new study by Kiat & O’Connor (2024) published in the Proceedings of the National Academy of Sciences provides strong additional support to the neoflightless hypothesis (also see the press releases by Field Museum 2024 and Koumoundouros 2024). The scientists studied the wing feathers in hundreds of different living bird species of all major orders, and detected a simple pattern that reliably distinguishes secondarily flightless birds from those that can fly: the latter always have 9-11 asymmetrical flight feathers called primaries, while the former have either significantly more or none at all. Furthermore, the degree of primary vane asymmetry turned out to be strongly related to flight. This allowed the researchers to look at 65 species of fossil birds and feathered dinosaurs to estimate their ability to fly. Unsurprisingly, Archaeopteryx and the four-winged Microraptor passed the litmus test for flight.

Much more surprisingly, the study suggests that feathered dinosaurs like “Caudipteryx possessed the correct number of primary feathers but they were almost completely symmetrical, ‘almost certainly’ ruling out flight” (Koumoundouros 2024). The authors concluded that “applying these data to extinct pennaraptorans suggests that anchiornithines and the oviraptorosaur Caudipteryx are secondarily flightless. The phylogenetic position of these species suggests that volant abilities are plesiomorphic to Pennaraptora.” In other words, all those feathered dinosaurs originally had wings like birds and could fly, and thus do not represent transitional stages in the evolution of avian flight from cursorial dinosaurs. They are no help at all to explain the origin of pennaceous feathers and wings. This also makes very recent studies obsolete, which proposed scenarios to derive the bird wing from more primitive structures in maniraptoran dinosaurs, such as the propatagium in Caudipteryx and Microraptor (Uno & Hirasawa 2023, also see University of Tokyo 2023). As new data accumulate at an ever faster rate, the shelf life of evolutionary story telling is plummeting from decades to only months.

Trust the Science?

Should you really just trust the science (but not too long)? Alan Feduccia can rightfully claim an important empirical confirmation of his theory, and Darwinists may have to say goodbye to some cherished assumed transitional forms and the evolutionary just-so stories built upon them. But there is more: Kiat & O’Connor (2024) explicitly admit that “the results of these analyses support a single origin of dinosaurian flight and indicate the early stages of feathered wing evolution are not sampled by the currently available fossil record.” It looks very much like flying vertebrates with feathered wings appeared fully formed and abruptly in the Jurassic, which resonates perfectly with intelligent design theory, but with Darwinism (in the sense of unguided gradual evolution) not so much.

References

• Feduccia A 1980. The Age of Birds. Harvard University Press, Cambridge (MA), ix+196 pp.
• Feduccia A 1996. The Origin and Evolution of Birds. Yale University Press, New Haven (CT), 420 pp. 
• Feduccia A 2012. Riddle of the Feathered Dragons: Hidden Birds of China. Yale University Press, New Haven (CT), x+358 pp.
• Feduccia A 2020. Romancing the Birds and Dinosaurs: Forays in Postmodern Paleontology. Brown Walker Press, Irvine (CA), 336 pp.
• Field Museum 2024. The hidden rule for flight feathers and how it could reveal which dinosaurs could fly. Phys.org February 12, 2024. https://phys.org/news/2024-02-hidden-flight-feathers-reveal-dinosaurs.html
• Geist N 2022. Romancing the Birds and Dinosaurs: Forays in Postmodern Paleontology. Ornithology 139(3), 1–2. DOI: https://doi.org/10.1093/ornithology/ukac013
• James FC 2021. How Many Dinosaurs Are Birds? Bioscience 71(9), 991–994. DOI: https://doi.org/10.1093/biosci/biab060
• Kiat Y & O’Connor JK 2024. Functional constraints on the number and shape of flight feathers. PNAS 121(8): e2306639121. DOI: https://doi.org/10.1073/pnas.2306639121
• Koumoundouros T 2024. Scientists Discover an Ancient Pattern Hidden in The Feathers of Birds. ScienceAlert February 25, 2024. https://www.sciencealert.com/scientists-discover-an-ancient-pattern-hidden-in-the-feathers-of-birds
• Leigh EG 2014. Alan Feduccia’s Riddle of the Feathered Dragons: what reptiles gave rise to birds? Evolution: Education and Outreach 7: 9, 1–3. DOI: https://doi.org/10.1186/s12052-014-0009-0
• Ostrom JH 1994. On the origin of birds and of avian flight. pp. 160–177 in: Prothero DP & Schoch RS (eds). Major Features of Vertebrate Evolution. University of Tennessee Press, Knoxville (TN), 270 pp.
• Ruben J 1997. The fuss over feathers. BioScience 47(6), 392–395. DOI: https://doi.org/10.2307/1313154
• University of Tokyo 2023. How birds got their wings. Phys.org February 24, 2023. https://phys.org/news/2023-02-birds-wings.html
• Uno Y & Hirasawa T 2023. Origin of the propatagium in non-avian dinosaurs. Zoological Letters 9: 4, 1–8. DOI: https://doi.org/10.1186/s40851-023-00204-x

Even Darwinists are admitting that junk DNA is junk no more?

 

Yet more on junk DNA's exposure as junk science.

 

There is no man called Jesus Christ?

 Luke ch.2:11NIV"Today in the town of David a Savior has been born to you; he is the Messiah, the Lord."

JEHOVAH Continues to school his would be correctors

 Is the Panda’s Thumb Suboptimal?

Stephen Dilley

In a classic argument, Stephen Jay Gould claimed that the panda’s thumb was suboptimal and, thus, counted as evidence in favor of evolution over special creation. In the contemporary era, this argument has become something of an icon as well as a broader symbol of the apparent problem of suboptimality in nature.1 If nature is the product of an intelligent designer, why are some biological phenomena so poorly made? In a recent peer-reviewed essay in the journal Religions, I revisited Gould’s argument as a way into this question and others like it.2 In a series of five posts here, of which this is the first, I will analyze the subject in some detail.

Here is the abstract of my article for Religions:

The panda’s thumb argument, championed by the late Stephen Jay Gould, stands as one of the most famous polemics for common ancestry. In this essay, I analyze Gould’s argument in several steps. First, I attempt to reconstruct the argument in both deductive and likelihood formulations. I contend that both versions of the argument rest on a theological claim — roughly, that God would not (likely) create or allow a suboptimal panda’s thumb. I then argue that a wide range of people are not rationally obligated to accept this theological claim. Next, I give special attention to the likelihood formulation’s emphasis on a contrastive argument for evolution over special creation. I contend that a great number of people are not rationally obligated to accept this formulation either. I next consider and reply to an objection that Gould never intended the panda argument as an apologetic for evolution (and an attack on special creation) but rather as a critique of adaptationism. Finally, I argue that the panda argument conflicts with Gould’s broader views about the human mind and the relationship between theology and science. I also note along the way that the shortcomings of the panda argument apply to a number of other arguments for evolutionary theory. To be sure, I do not criticize evolution itself or the comprehensive grounds for it. Instead, my primary aims are to analyze the panda argument and suggest that caution is in order about similar arguments as well.

Let’s first consider the crucial empirical question of whether the panda’s thumb is indeed suboptimal. Is it “clumsy” and “highly inefficient,” as Gould claims it to be? Or does it perform its function just fine? In subsequent posts, I will analyze more philosophical questions and topics: Is the panda argument a problem for intelligent design scientists? And is the panda argument a problem for evolutionists? 

Clumsy, Clumsy, Clumsy

As to the question of suboptimality, the answer centers on the thumb’s function. Gould thinks it does its job in a mediocre way. He notes that Darwin thought much the same about orchids. Gould explains:

The panda’s thumb provides an elegant zoological counterpart to Darwin’s orchids. An engineer’s best solution is debarred by history. The panda’s thumb is committed to another role, too specialized for a different function to become an opposable, manipulating digit. So the panda must use parts on hand and settle for an enlarged wrist bone and a somewhat clumsy, but quite workable solution. The sesamoid thumb wins no prize in an engineer’s derby.3

He also explains:

The panda’s “thumb” demonstrates evolution because it is clumsy and built from an odd part, the radial sesamoid bone of the wrist. The true thumb had been so shaped in its ancestral role as the running and clawing digit of a carnivore that it could not be modified into an opposable grasper for bamboo in a vegetarian descendant.4

At the heart of Gould’s argument is the claim that the panda’s thumb is “clumsy” or, as he says elsewhere, “highly inefficient.”5

Gould explains that suboptimality favors evolution whereas “ideal design” favors special creation.

[I]deal design is a lousy argument for evolution, for it mimics the postulated action of an omnipotent creator. Odd arrangements and funny solutions are the proof of evolution — paths that a sensible God would never tread but that a natural process, constrained by history, follows perforce.6

The basic argument is that “[o]dd arrangements and funny solutions” point to evolution whereas “ideal design” points to a “sensible God.” Given that the panda’s thumb “wins no prize in an engineer’s derby,” it supports evolution rather than divine design.

The Empirical Evidence

Yet the scientific data say otherwise. As I explain in the article:

Oddly, Gould does not give strong reasons to accept this claim [that the panda’s thumb is suboptimal]; nowhere in his writings does he provide a detailed empirical study that demonstrates the suboptimality of the panda’s thumb. The major research that Gould relies upon, Dwight Davis’s study, used a dead panda for its conclusions about comparative morphology; it did not examine how effective living pandas are at stripping bamboo leaves. Biologist John Gittleman notes that the analyses of both Davis and Gould arose “despite any real information on how the giant panda lives in nature.”7

Two major studies gave high praise to the function and efficiency of the panda’s thumb:

The first major study of living pandas — focusing specifically on their adaptation to bamboo — was conducted by George Schaller’s team, which published its results in The Giant Pandas of Wolong. They observed that pandas “efficiently bring food to the mouth with their forepaws” and “handle bamboo stems with great precision by holding them as if with forceps in the hairless groove connecting the pad of the first digit and pseudothumb.”8

Schaller and his team reported:

When watching a panda eat leaves, stem or new shoots we were always impressed by its dexterity. Forepaws and mouth work together with great precision, with great economy of motion, as the food is grasped, plucked, peeled, stripped, bitten and otherwise prepared for being swallowed. Actions are fluid and rapid…9

Similarly, in 1999, a team of Japanese scientists conducted perhaps the most sophisticated analysis of the panda’s thumb to date. They used “computed topography, magnetic resonance imaging, and live observation to analyze the structure and function of the panda’s thumb.” They reported that the thumb 

and its accessories enable the panda to “manipulate objects with great dexterity.” In fact, the “way in which the giant panda, Ailuropoda melanoleuca, uses the radial sesamoid bone — its ‘pseudo-thumb’ — for grasping makes it one of the most extraordinary manipulation systems in mammalian evolution.” They conclude that “the hand of the giant panda has a much more refined grasping mechanism than has been suggested in previous morphological models,” including Davis’s model.10

Turning the Tables

Gould’s claim is mistaken. The panda’s thumb is not suboptimal. The best studies we have conclude that the thumb is anything but “clumsy” or “highly inefficient.” Instead, they describe it as having “great precision,” “great economy of motion,” and “great dexterity.” It may even rank as “one of the most extraordinary manipulation systems” among mammals. That is quite an accolade.

Indeed, one might rather regard the thumb as positive evidence for intelligent design. A system of such precision, efficiency, economy, and dexterity is a spectacle of a high order. That sounds very much like the kind of sophistication that only engineers produce. 

On this score, recall the way Gould himself framed the panda argument: “[o]dd arrangements and funny solutions” point to evolution whereas “ideal design” points to a “sensible God.”11 So, by this logic, the panda’s thumb appears to count as stronger evidence in favor of design. Perhaps it’s time to champion the panda’s thumb not as an icon for evolution but for intelligent design

Notes

See Dilley, “God, Gould, and the Panda’s Thumb,” p. 1.

Stephen Dilley. 2023. “God, Gould, and the Panda’s Thumb.” Religions 14: 1006. https://doi.org/ 10.3390/rel14081006.

Stephen Jay Gould. 1980. The Panda’s Thumb. New York: W.W. Norton, p. 24.

Gould, The Panda’s Thumb, p. 29, original emphasis.

Stephen Jay Gould. 1986. “Evolution and the Triumph of Homology, Or Why History Matters.” American Scientist 74: 60-69, esp. p. 63.

Gould, The Panda’s Thumb, p. 20-21.

Dilley, “God, Gould, and the Panda’s Thumb,” p. 11. For the Gittleman quote, see John L. Gittleman. 1985. “Review of The Giant Pandas of Wolong.” The Quarterly Review of Biology 60: 524. 

Dilley, “God, Gould, and the Panda’s Thumb,” p. 11. For the Schaller quote, see George B. Schaller, Hu Jinchu, Pan Wenshi, and Zhu Jing. 1985. The Giant Pandas of Wolong. Chicago: University of Chicago Press, p. 4, 215.

Schaller et al., The Giant Pandas of Wolong, p. 58.

Dilley, “God, Gould, and the Panda’s Thumb,” p. 11. See also Hideki Endo, Daishiro Yamagiwa, Yoshihiro Hayashi, Hiroshi Koie, Yoshiki Yamaya, and Junpei Kimura. 1999. “Role of the Giant Panda’s ‘Pseudo-thumb’.” Nature 397: 309-10.

Gould, The Panda’s Thumb, p. 20-21.

Engineerless engineering is a thing?

 Design Without a Designer? New Book Says Yes!

Daniel Witt

The more we learn about living systems, the harder they are to explain without invoking teleology — purpose, planning, goal. If an intelligent designer is off the table, this creates a dilemma for some. 

Wouldn’t it be great if you could have your cake and eat it too — have design, without a designer? In 2023, MIT Press released an edited volume of papers by prominent biologists and philosophers of science titled Evolution “On Purpose”: Teleonomy in Living Systems. The purpose of the volume is to promote the theory of “teleonomy.” Teleonomy is “internal teleology” — goal-directedness that comes from within a system, not from outside. Under this theory, there need be no God (or aliens, or Platonic or Aristotelian forms, or anything of the sort) guiding the development of living systems; the living systems themselves set the goals.

The “Unspoken” Inference 

Biologist Peter Corning, one of the editors of the volume, writes: 

The evolution of humankind is undoubtedly the most striking example of how teleonomy has exerted a shaping influence in biological evolution, but a case can be made that teleonomy was also involved in many of the great turning points and transitions in the history of life on Earth, including the earliest colonization of the seafloor, the emergence of the eukaryotes, the migration of life forms from the oceans onto the land, the rise of multicellular organisms, the development of land plants and trees, the origin of fish, birds, and mammals, the invention of social organization, the division of labor (task specialization), and more. 

Teleonomy is also an implicit (though unspoken) influence in connection with many other familiar terms, I would argue, including “symbiogenesis,” “organic selection theory,” evolutionary “pacemakers,” the “Baldwin effect,” “major transitions theory,” “niche construction theory,” “gene-culture coevolution theory,” “natural genetic engineering,” many examples of “semiosis,” and, recently, the concept of “agency” in evolution. These terms all suggest the role of purposive behavior. A radically different view of evolution has been emerging in this century. We now know that living systems actively shape their own evolution, in various ways.

In other words, Corning is saying that all sorts of evolutionary theories contain the hidden assumption of purposiveness, i.e., design. This is an important admission, since it’s what ID theorists have been saying. 

Of course, he differs on where this design comes from. But it’s worth noting that the thesis of teleonomy implicitly acknowledges the validity of the design inference. If you can infer design in nature, you can infer design in nature. Period. Then you can decide whether it comes from within or from without.

That means that if the teleonomic explanation (“living systems actively shape their own evolution”) doesn’t hold up, the old alternative hypothesis will be there, waiting. 

Is Teleonomy a Good Explanation? 

So, does the teleonomic explanation hold up? Well, we have to ask: where does “teleonomy” come from? Why does it exist? 

The answer, according to Evolution “On Purpose”, is that it come from… drum roll… evolution. In addition to causing evolution. 

The term “teleonomy,” Corning writes, was coined “to draw a contrast between an ‘external’ teleology (Aristotelian or religious) and the ‘internal’ purposiveness and goal-directedness of living systems, which are products of the evolutionary process and of natural selection.” However, teleonomy is “not simply a product of natural selection. It is also an important cause of natural selection and has been a major shaping influence over time in biological evolution.” Conversely, natural selection “has been both a cause of this purposiveness and an outcome.”

This is not, in itself, illogical. You could have two forces at work — purpose and natural selection — that synergistically encourage each other, in a sort of positive feedback loop. But then, you still have to explain how the feedback loop got started. 

Imagine that someone asks an evolutionary biologist where chickens came from. 

“Eggs,” the scientist replies. 

“Where did eggs come from?” his interlocuter replies. 

“Chickens!” says the scientist. 

The problem with this explanation is not that it is false. As it happens, it is quite true. The problem is that it fails to explain. It does not answer the question that was really being asked.

Likewise, “teleonomy” fails to explain. The design of nature requires an explanation, an ultimate explanation. Rather than explain, invoking “teleonomy” just dodges the question. If we say that natural selection and random variation cannot explain something, evolutionary biologists can say, “Well, it’s not random variation, it’s goal-oriented.” If we ask where the goal-oriented-ness itself came from, they will say “natural selection.” The question returns to where it began; a final cause for the existence of design in nature has yet to be proposed.

Avoiding the Question

I suspect it will never be proposed, because the point is to sweep the problem under the rug by obscuring it in a complexity of causes. The theory of teleonomy does not address — is not even in dialogue with — the arguments of, say, Michael Behe or William Dembski that unguided processes simply cannot generate novel information or irreducibly complex systems. But it does make it harder to apply those arguments, because there is nothing concrete to discuss. We are not talking about a bacterial flagellum, or an eye, or even a brain — we are talking about a vague internal “purposiveness.” This purposiveness, if it exists and is not supernatural, would have to arise from some organized and complex system. But the exact nature of that system is hidden somewhere in an endless chain of “purposiveness caused by natural selection caused by purposiveness caused by natural selection…” going back who knows how far.

In future posts, I plan to discuss some of the specific mechanisms for evolution proposed in the Evolution “On Purpose”anthology. However, this is the basic problem that underlies the whole endeavor. At the end of the day, ordered complexity requires either extreme luck or intentional planning. The idea that life itself did this planning may sound like a clever work-around, but in the end it’s no better than the idea of a god who created himself. 

Nothing can create itself. Everything has a cause, until you get back to some eternal First Cause. Any attempt to avoid that logical destination is just stalling. 

Information is in the mind of the informed?

 The Connection Between Intelligence and Information

Willam Dembski

The key intuition behind the concept of information is the narrowing of possibilities. The more that possibilities are narrowed down, the greater the information. If I tell you I’m on planet Earth, I haven’t conveyed any information because you already knew that (let’s leave aside space travel). If I tell you I’m in the United States, I’ve begun to narrow down where I am in the world. If I tell you I’m in Texas, I’ve narrowed down my location further. If I tell you I’m forty miles north of Dallas, I’ve narrowed my location down even further. As I keep narrowing down my location, I’m providing you with more and more information.

Information is therefore, in its essence, exclusionary: the more possibilities are excluded, the greater the information provided. As philosopher Robert Stalnaker put it in his book Inquiry: “To learn something, to acquire information, is to rule out possibilities. To understand the information conveyed in a communication is to know what possibilities would be excluded by its truth.” I’m excluding much more of the world when I say I’m in Texas forty miles north of Dallas as opposed to when I say I’m merely in the United States. Accordingly, to say I’m in Texas north of Dallas conveys much more information than simply to say I’m in the United States.

An Exclusionary Understanding

The etymology of the word information is congruent with this exclusionary understanding of information. The word information derives from the Latin preposition in, meaning in or into, and the verb formare, meaning to give shape to. Information puts definite shape into something. But that means ruling out other shapes. Information narrows down the shape in question. A completely unformed shmoo is waiting in limbo to receive information. But until it is given definite shape, it exhibits no information.

The fundamental intuition of information as narrowing down possibilities matches up neatly with the concept of intelligence. The word intelligence derives from two Latin words: the preposition inter, meaning between, and the verb legere, meaning to choose. Intelligence thus, at its most fundamental, signifies the ability to choose between. But when a choice is made, some possibilities are actualized to the exclusion of others, implying the narrowing of possibilities. And so, an act of intelligence is also an act of information.

A Narrowing of Possibilities

A synonym for the word choose is decide. This last word is likewise from the Latin, combining the preposition de, meaning down from, and the verb caedere, meaning to cut off or kill (compare our English word homicide). Decisions, in keeping with this etymology, raise up some possibilities by cutting down, or killing off, others. When you decide to marry one person, you cut off all the other people you might marry. An act of decision is therefore always a narrowing of possibilities. It is an informational act. But given the definition of intelligence as choosing between, it is also an intelligent act.

Given the etymology of information and intelligence, it’s obvious that the two are related notions. The million dollar question in connecting the two is how we can know when an intelligence is actually responsible for an item of information. Information can happen naturally — a rock falls naturally here rather than there. But information can also happen intelligently — a rock may be put deliberately here rather than there. So how do we tell the difference? 

Answering that question is the whole point of specified complexity and the design inference. If you’ve got the time and inclination to probe this question deeply, get the book: William A. Dembski and Winston Ewert, The Design Inference, 2nd edition. Otherwise, stay tuned here — I’ll be providing a user-friendly synopsis of how to know when an intelligence is responsible for information.

Postscript

The featured image here may look like a random inkblot, but it’s not. Many people don’t at first see what’s there. Once they see it, they know that the information there is the product of intelligence. But until then, they would be within their rights to think that it’s just a random naturally-formed inkblot.

Tangible evidence for design?

 Sense of Touch Is More Finely Tuned than We Thought

David Coppedge

“Reach out and touch someone.” Some may remember that old TV commercial. Bell Telephone appealed to the human need for communication to grow its business, implying that a phone call was the next best thing to a hug or handshake. At a scale five orders of magnitude smaller, cells also like to reach out and touch their neighbors. They respond not with ears and fingers, but with channels that open on contact, making intercellular communication come alive.

In a previous article about active transport and selectivity filters, we marveled at the precision alignment of amino acid residues in the CFTR channel that employ electrostatic forces to authenticate chloride ions passing through a narrow “selectivity filter” required for entry. CFTR channels remain open all the time for their chloride ion customers. Others require a touch, like the push of a button on a vending machine, to activate. 

A Biological Piezoelectric Effect

One such channel has an interesting name, Piezo2, reminiscent of the piezoelectric effect in physics where applying mechanical stress to certain materials generates electricity. You may have seen a demonstration of this effect when a physics teacher hit a quartz rock with a hammer and generated sparks. In a related way but with different physics, Piezo channels are touch sensitive, and indeed are crucial for our sense of touch.

We have numerous Piezo1 channels in our skin, which respond on contact by opening to let Ca2+ ions flood into the cell, triggering neural signals interpreted by the brain as touch. Piezo2-deficiency syndrome, caused by mutations in the PIEZO2 gene, manifests as decreased touch sensation and proprioception, leading to difficulty walking and loss of coordination. The Piezo2 channel has a curious shape, with a dome of three curved arms that look like propeller blades.

News from the Max Delbrück Center adds a partner to Piezo2. 

Every hug, every handshake, every dexterous act engages and requires touch perception. Therefore, it is essential to understand the molecular basis of touch. “Until now, we had known that the ion channel — Piezo2 — is required for touch perception, but it was clear that this protein alone cannot explain the entirety of touch sensation,” says Professor Gary Lewin, head of the Molecular Physiology of Somatic Sensation Lab at the Max Delbrück Center.

For over 20 years Lewin has been studying the molecular basis of the sensation of touch. He and his team have now discovered a new ion channel, named Elkin1, that plays a vital role in touch perception. This is only the second ion channel implicated in the touch perception.

Like other ion channels, Elkin1 is anything but simple. It contains 7 transmembrane proteins with a well-defined structure and selectivity filter. Lewin’s team, who published their findings in Science, first noticed that mice without functional Elkin1 often had reduced touch sensitivity. Then they checked to see if the two mechanically activated (MA) channels cooperated. Strangely, they did not — at least directly. Elkin1, instead, interacts with StomL3, a modulator of Piezo2 sensitivity. Further tests revealed a cooperative role in these three proteins that permits response to low-threshold mechanoreceptors (LTMRs).

Our data support a model in which ELKIN1 and PIEZO2 channels share roles in sensory mechanotransduction in LTMRs and in which both channels can be modulated by STOML3. There is evidence that STOML3 can also modulate MA currents in nociceptors, which is consistent with a role for ELKIN1 in conferring robustness to the C-fiber responses to force. The identification of ELKIN1 as a mechanically gated ion channel necessary for somatosensory function increases our understanding of the entirety of touch transduction.

Cooperation between these three actors gives an animal a wide range of touch sensitivity, from a quick light touch to constant pressure at the point of pain. The take-home lesson is that the sense of touch now looks more complex and more finely tuned than thought. One mechanoreceptor is not enough for exquisite responses to touch, whether it be a hug, handshake, or dexterous act.

Touch-Sensitive Tissue Repairmen

An open access paper by a team from Yale in Science Advances tells about another discovery in mechanosensation. Macrophages, part of the immune system, reside in the extracellular matrix of many tissues. When they sense a disturbance in the force, they slither about like amoebas to the site of repair. Having DNA credentials, they can also signal the nucleus to send reinforcements.

Tissue-resident macrophages play important roles in tissue homeostasis and repair. However, how macrophages monitor and maintain tissue integrity is not well understood. The extracellular matrix (ECM) is a key structural and organizational component of all tissues. Here, we find that macrophages sense the mechanical properties of the ECM to regulate a specific tissue repair program. We show that macrophage mechanosensing is mediated by cytoskeletal remodeling and can be performed in three-dimensional environments through a noncanonical, integrin-independent mechanism analogous to amoeboid migration.We find that these cytoskeletal dynamics also integrate biochemical signaling by colony-stimulating factor 1 and ultimately regulate chromatin accessibility to control the mechanosensitive gene expression program. This study identifies an “amoeboid” mode of ECM mechanosensing through which macrophages may regulate tissue repair and fibrosis.

Lysosomes: Organelles with Mechanosensitive Channels

Not all mechanosensitive channels reside on the external lipid membranes of cells. Here’s one on the membrane of an important organelle: the lysosome. Li et al., publishing in Nature (open access), explored a protein named TMEM63 that works in a mechanosensitive channel on the membranes of lysosomes. Erika Reiderer and Dejian Ren, commenting on this paper in the same Nature issue, describe the lysosome as “a vital organelle with an acidic pH that digests and recycles cellular materials thanks to more than 50 digestive enzymes and many transporters.” Now, one of those parts turns out to be an intercellular mechanosensitive ion channel.

Because lysosomes are embedded in signaling networks with other organelles, it makes sense that they often feel the need to reach out and touch someone. The busy interior of a cell makes contacts unavoidable and frequent. A figure in the commentary shows mechanical stimuli impinging on the lysosome’s membrane in various ways. The TMEM3 channels interact with signals from other organelles such as mitochondria, peroxisomes, the endoplasmic reticulum (ER) via their tethering proteins, effectors and transporters; microtubules being carried by motor proteins; endosomes coming in from the exterior; nutrient sensors via the mTORC1 pathway; and possibly mechanical signals from the V-ATP rotary motors embedded in the lysosomal membrane. (V-ATPases, by the way, rotate similarly to ATP synthase, but hydrolyze ATP for protons to acidify the interior of the lysosome.) A politician could hardly shake more hands than these contact-sensitive TMEM63 channels do constantly!

Li’s team was able to measure electrical currents in these TMEM63 channels, which is truly remarkable, given that they were measuring conductance on the membranes of tiny organelles in response to mechanical forces inside the cells of fruit flies! They even measured the pressure that triggered the responses. What amazing times we live in, where such measurements are possible, and we can image the molecular machines themselves. The team also investigated comparable channels named TMEM63A in mice, one of three mammalian counterparts found in our bodies, too. No mention was made of evolution, other than to note that all these homologues are “evolutionarily conserved” — i.e., unevolved.

Reiderer and Ren consider this a groundbreaking discovery ripe for more research. 

The Li et al. study opens a new frontier in lysosomal physiology. As with many other groundbreaking discoveries, it also prompts more questions than answers. How is lysosomal TMEM63 opened by mechanical force? Does it functionally or physically interact with other, better-known lysosomal channels to coordinate lysosomal physiology and cellular signalling? How does a mechanosensing channel regulate a lysosomal function as basic as substrate digestion? Is the channel also regulated by organelle membrane lipids and extracellular cues, such as nutrients and growth factors? Finally, the mechanisms for sensing mechanical forceby plasma membranes are — somewhat annoyingly to physiologists — highly diverse between cells and across species. Are the mechanisms used by lysosomes more uniform? With the newly found role of TMEM63, it is hoped that these questions can be answered shortly.

Answers will come from engineers specializing in biophysics. It’s the kind of research favorable to ID, where scientists investigate a phenomenon on the assumption that if something exists and is working, it has a purpose.

A great physicist does not = a great atheist?

 My Dinner with Steven and Louise Weinberg

William A Dembski

In the late 1990s, a number of us had dinner with Steven Weinberg and his wife Louise at a restaurant in Austin, Texas. Weinberg as well as his wife were on faculty there at the University of Texas, he in physics, she in law. Another faculty member had arranged a public exchange at the university between Weinberg and Phil Johnson, Johnson at the time being a key figure in challenging naturalism and advancing intelligent design. After the exchange, we went to dinner.

A Towering Figure

Weinberg, who died in 2021, was a towering figure in 20th-century physics. Yes, he had a Nobel Prize. But he was a big deal even among fellow Nobel Prize winners. Besides a stupendous record of achievement in physics, he was also a great writer whose popular treatments of science, such as The First Three Minutes, sold well and made him not just a physicist but also a public intellectual.

I remember two things especially about the dinner. Weinberg was very smart and let you know it. He was also an outspoken atheist, and it would have taken courage to confront him on his atheism (which Phil Johnson did). But it was interesting at the dinner to hear from Weinberg a key reason why he rejected theism, namely, he knew Christians physicists who hesitated to share with him their faith. As he put it, if Christianity is true and Jesus is so important, why don’t they talk to me about their faith? 

I’m not sure how much stock to put in Weinberg’s objection. The faculty member who set up the exchange with Johnson and then the dinner wasn’t hiding his faith, nor was Johnson. But Weinberg’s objection raises an interesting point about how much faith goes unshared because we are intimidated by the people with whom we might otherwise share our faith. The consistent testimony of Scripture is that we should fear God and not man.

Not a Great Atheist

The high point of the dinner for me, however, came from his wife Louise. Weinberg was holding court, going on about how much he knew about the origin of the universe and how atheism was the only intellectually viable option. Louise turned to the table and remarked that scientists like Weinberg, who are accomplished in one area, think they speak with authority in every area, but they can’t. 

It was like air being let out of a tire. For all of Weinberg’s bluster and confidence, it was heartwarming to see him meekly accept his wife’s correction. As an attorney and law professor, Louise knew that there are no universal expert witnesses in a court of law. Weinberg was a great physicist. But he wasn’t a great atheist. And I say this to his credit.

I personally suspect that Weinberg had doubts about his atheism, and that his atheism was more a pose than a reflection of his heart. One reason I say this is that Weinberg seemed always ready to engage theists. A few years after the dinner, I helped organize a conference at Baylor titled “The Nature of Nature.” Weinberg agreed to be a speaker at the conference if we would provide a limo for the 100 mile trip from Austin to Waco. Of course, we obliged. It was an honor to have him.

Can our AI overlords be trusted.

Truth and Trust in Large Language Models

William Dembski 

The trust we put in Large Language Models (LLMs) ought to depend on their truthfulness. So how truthful are LLMs? For many routine queries, they seem accurate enough. What’s the capital of North Dakota? To this query, ChatGPT4 just now gave me the answer Bismarck. That’s right.

But what about less routine queries? Recently I was exploring the use of design inferences to detect plagiarism and data falsification. Some big academic misconduct cases had in the last 12 months gotten widespread public attention, not least the plagiarism scandal of Harvard president Claudine Gay and the data falsification scandal of Stanford president Marc Tessier-Lavigne. These scandals were so damaging to these individuals and their institutions that neither is a university president any longer. 

When I queried ChatGPT4 to produce 25 cases of academic research misconduct since 2000 (as part of my project to understand how design inferences might help preserve academic integrity), seven of those accused of academic misconduct either were plainly innocent or could not reasonably be charged with misconduct for lack of evidence. In one case, the person charged by ChatGPT4 had actually charged another academic with misconduct. It was as though ChatGPT4 in this instance could not distinguish between someone being charged with misconduct and someone issuing a charge of misconduct.

Hallucinations

Ever since LLMs took the world by storm in late 2022, I’ve attempted to put them through their paces. They do some things well. I find them a valuable assistant. But they can also be misleading to the point of deception. Not that these systems have the volitional intent to deceive. But if we treated them as humans, they could rightly be regarded as deceptive. Anyone who has worked with LLMs has learned a new meaning for the word “hallucinate.” That’s what LLMs do when they make stuff up. 

I’ve witnessed plenty of LLM hallucinations first hand, such as false accusations of academic misconduct. Let me offer two additional salient examples in my experience. First, I was helping with a Halloween story for an educational website. The story was to list the “scariest buildings on college campuses.” I had ChatGPT4 pull together a list of forty or so such campus buildings along with a description of what made each scary. With building after scary building I kept reading that it was “gothic.” Eventually I said to myself, “Wait a minute. There aren’t that many gothic buildings on college campuses.” True enough, many buildings on the list said to be gothic were anything but gothic. The LLM I queried had been trained to associate scary with gothic, and so it just kept describing these buildings as gothic — regardless of their actual architecture.

The other example involved a search for quotes from prominent biologists extolling the beauty, elegance, and sophistication of biological systems. I wanted such quotes in responding to dysteleological arguments by Darwinian biologists claiming that biological systems are jury-rigged Rube Goldberg devices that give no evidence of exquisite design. So I queried an LLM for quotes extolling biological design. I got plenty such quotes and they were assigned to prominent biologists. I also got some article references from which those quotes were supposedly taken. But it was all made up — the quotes, the references, and the assignment of biologists to those quotes (the biologists themselves were real). 

Practical Advice

The obvious lesson here for LLMs is, Verify first and only then trust. This advice makes good practical sense. In particular, it helps prevent the embarrassment of reproducing hallucinated content from LLMs. It also makes good legal sense. The following from a March 29, 2024, Wall Street Journal article titled “The AI Industry Is Steaming Toward a Legal Iceberg” is self-explanatory:

If your company uses AI to produce content, make decisions, or influence the lives of others, it’s likely you will be liable for whatever it does — especially when it makes a mistake… The implications of this are momentous. Every company that uses generative AI could be responsible under laws that govern liability for harmful speech, and laws governing liability for defective products — since today’s AIs are both creators of speech and products. Some legal experts say this may create a flood of lawsuits for companies of all sizes.

Whether companies that produce AI-generated content can issue strong enough disclaimers to shield themselves from liability remains to be seen (can disclaimers even provide such protection?). Such a terms-of-use disclaimer might read: “Users of this LLM agree to independently verify any information generated by this LLM. The creators of this LLM take no responsibility for how the information generated by this LLM is used.” This would be like disclaimers in books on alternative healing, which shift the burden of liability to mainstream medicine: “This book is not intended to serve as medical guidance. Before acting on any recommendations presented in this book, readers should seek the advice of a physician.” 

But there’s another sense in which the advice to verify the output of LLMs is not at all practical. LLMs allow for the creation of content at a scale unknown till now. They are being used to generate massive amounts of content, causing entire websites to magically materialize. There is now a rush to push out content as a business exigency. Sites that depend purely on humanly written content are likely to lose any competitive advantage. 

How likely is it, then, that such LLM-generated content will be carefully scrutinized and thoroughly vetted? What if this content is untrue but nothing much is riding on its truth? What if no one will hold the content, or its supposed author, to account? In that case, there will be incentives to cut corners and not worry about LLM hallucinations. Others are doing it. LLMs are a force multiplier. The need to accelerate content creation is urgent. So if you want to stay in this rat race, you’ve got to be a rat. 

The Need for Independent Verification

A commitment to verification will put the brakes on content creation from LLMs. Yes, verification will slow you down. But what you lose in quantity you may well regain in quality and credibility (unless you don’t care about these). In fact, if your commitment to verification is thorough-going, you may be justified in putting a disclaimer on your site that inspires confidence, such as: “All content on this site generated with the assistance of LLMs has been independently verified to be true.” 

Of course, you might even prefer a disclaimer that simply reads: “All content on this site was written by humans and produced without the assistance of LLMs.” But such a disclaimer may be hard to maintain, especially if your site is drawing material from other sources that may have used LLMs. All content these days is likely to feel the effects of LLMs. One might say that it has all been infected or tainted by LLMs. But that seems too strong. As long as content generated by LLMs is properly vetted and edited by humans, it should pose no issues.

Obviously, as part of any disclaimer that assures independent verification, such verification must mean not subjecting a claim made by one LLM to another LLM. Consider, for instance, the following query to ChatGPT4 about myself. As it is, many critics of intelligent design characterize me as a pseudoscientist. I regard this characterization as unfair and unjustified, and I have a publication record to back me up on this. But consider the following exchange with Google’s Gemini:

ME: Is William A. Dembski a legitimate scientist?

GEMINI: William A. Dembski’s credentials are interesting. He has a Ph.D. in mathematics and has done published work in various fields. However, his work on intelligent design is considered pseudoscience by the vast majority of scientists… So, while Dembski has scientific credentials, his work on intelligent design is not considered legitimate science.

So let’s now go to OpenAI’s ChatGPT4 and ask it to assess Gemini’s answer:

ME: Please evaluate the following assessment of William A. Dembski’s legitimacy as a scientist: “William A. Dembski’s credentials are interesting. He has a Ph.D. in mathematics and has done published work in various fields. However, his work on intelligent design is considered pseudoscience by the vast majority of scientists… So, while Dembski has scientific credentials, his work on intelligent design is not considered legitimate science.”

CHATGPT4: This assessment of William A. Dembski’s legitimacy as a scientist is accurate… The assessment fairly represents the dichotomy between Dembski’s academic qualifications and the acceptance of his work on intelligent design within the scientific community. It underscores the importance of distinguishing between an individual’s credentials and the scientific validity of their work, based on the norms and standards of the scientific method.

Of course, critics of my work may think that Gemini and ChatGPT4 nailed their assessment of me. But even such critics should appreciate that using one LLM to vet another is a fool’s errand. Independent verification is required. And that may mean (gasp) veering outside of Wikipedia. Portions of Wikipedia are outdated, biased, or simply wrong. Because LLMs tend to draw so heavily on Wikipedia, independent verification means going beyond Wikipedia and, ideally, going to primary sources. 

Yet I also want to urge a deeper skepticism of LLMs. 

A Systemic Fault with LLMs

Up to now, it may seem that I’ve merely been advising caution with LLMs: Verify and only then trust. That certainly seems like sound advice for using LLMs. Yet I also want to urge a deeper skepticism of LLMs. Our knowledge of the world as expressed in language arises from our interactions with the world. We humans engage with a physical world as well as with a world of abstractions (such as numbers) and then form statements in words to describe that engagement. 

What does it mean for such statements to be true? Aristotle defined truth as to say of what is that it is and of what is not that it is not. Truth is thus fundamentally a correspondence relation between our words and the world. Many contemporary philosophers dismiss this understanding of truth, preferring pragmatic or coherentist conceptions of truth, arguing that there’s no rigorous way to characterize the correspondence relation that makes a statement true. 

Frankly, this is a boutique debate among philosophers that has little purchase among ordinary people. The sentence “Allan stole Betty’s purse” is true if the people referred to here exist, if Betty had a purse, and if Allan actually stole it. Whether there’s a way to make good philosophical sense of this correspondence between words and things is in fact irrelevant to our discussion about the truth of what LLMs tell us. LLMs, by being entirely enclosed in a world of words, are unengaged with the wider world that is the basis for our knowledge. 

Let this point sink in. I might know that Allan stole Betty’s purse because I witnessed Allan steal Betty’s purse. But LLMs can have no such experience. They consist of a neural network that assigns weights to relations among words and sentences. Suppose the verbal data that is the basis for this LLM included testimony about Allan’s theft but also claims about Allan being framed for the theft. How, then, does the LLM decide what truly happened? It cannot form a reasoned and responsible decision here as we humans might, weighing evidence and trying to reach a reasonable conclusion. Rather, the LLM’s data and training will determine whether to assign guilt or innocence to Allan.

But who trains the LLM? And who’s training the trainers? What are the guidelines they are expected to follow? And who decides what those guidelines are supposed to be? It’s the old problem of Quis custodiet ipsos custodes? (Who’s minding the minders?). Additionally, who determines the training data for the LLM? And who determines the data to which the LLM may be legitimately applied? Ultimately, the answer to all such questions will point to the decisions of a group of people, such as the programmers at OpenAI. And why should such a group be trusted?

Such questions underscore that LLMs have no substantive connection to truth. It’s not that an LLM knows the truth of what it is claiming. Rather, its training gives it a pretense of truth. An LLM needs as much as possible to give the appearance of being truthful because getting too many things obviously wrong will discredit the LLM. But its accuracy is at best a byproduct of trying to please human users. 

When I asked ChatGPT4 about scary buildings on college campuses, I would have preferred simply to be told “I don’t know.” But instead, LLMs are programmed to pretend to knowledge that they don’t have. Initially, it was gratifying for me to learn about all those scary college buildings. ChatGPT4 seemed to have saved me much effort in research — until, that is, I did an independent verification and actually looked at the images of some of the buildings cited. 

Granted, the pretense of truth in LLMs often yields results that are truthful (Bismarck is indeed the capital of North Dakota). But where there’s divergent testimony in the input data about the truth of a claim, the LLM’s training will decide what it deems true and what it deems false. That makes LLMs fundamentally untrustworthy. 

How Do LLMs Deal with Controversy?

Controversial topics provide an effective proving ground for LLMs and the challenges they face with truth and trust. Take, for instance, the hot-button topic of gender dysphoria. Here is an exchange I had with ChatGPT4

ME: In one paragraph describe the health concerns associated with gender dysphoria.

CHATGPT4: Gender dysphoria, characterized by a strong discomfort or distress due to a discrepancy between one’s gender identity and assigned sex at birth, can have significant health implications if not addressed. Individuals with gender dysphoria are at a higher risk for mental health issues, including anxiety, depression, and suicidal thoughts or behaviors, stemming from the internal conflict and societal pressures or stigma they may face. Additionally, the stress associated with gender dysphoria can lead to or exacerbate physical health problems, such as high blood pressure or cardiovascular disease, due to chronic stress. Those seeking gender-affirming treatments may also encounter health risks related to hormone therapy or surgical procedures, although these risks are often outweighed by the substantial mental health benefits and increased quality of life these treatments can provide. Access to comprehensive healthcare, social support, and gender-affirming treatments is crucial in mitigating the health concerns associated with gender dysphoria.

Note the text in bold, which clearly gives one particular perspective on gender dysphoria to the exclusion of others. It therefore minimizes the alternative view that sees gender-affirming care as deeply problematic and destructive (e.g., Abigail Shrier’s view as expressed in her book Irreparable Harm). To be clear, my point here is not to take sides on this issue. It is simply to point out that LLMs are trained to come up with certain answers, and that this training need not have any connection to ordinary canons of evidence or reason. 

One can try to circumvent the bias built into an LLM by posing the queries or prompts to it in ways that get the LLM itself to bypass the bias. Thus the query about gender dysphoria above might have been rephrased as follows:

ME: In one paragraph describe the health concerns associated with gender dysphoria as psychiatrists and psychologists would have understood them in the 1950s and 1960s (as with DSM1 and DSM2).

DSM1 and DSM2, earlier editions of Diagnostic and Statistical Manual produced back in the 1950s and 60s, regarded gender dysphoria as a mental illness and would therefore not have recommended anything like what is meant today by gender-affirming care. In that light, consider ChatGPT4’s response to this query:

In the 1950s and 1960s, the understanding of gender dysphoria by psychiatrists and psychologists, as reflected in the first two editions of the Diagnostic and Statistical Manual of Mental Disorders (DSM-I and DSM-II), was markedly different from today’s perspectives. During this era, gender dysphoria—or discomfort with one’s assigned gender at birth—was not explicitly categorized as it is now. Instead, related conditions might have been classified under broader, more generalized disorders such as “sexual deviation” or “transvestism” within the DSM. The medical and mental health communities of the time often viewed such gender nonconformity through a pathologizing lens, considering it a mental illness requiring treatment aimed at realigning the individual’s gender identity with their biological sex. The focus was less on the mental health implications of gender dysphoria itself — such as anxiety, depression, and identity distress — and more on the behaviors and identities diverging from societal norms. There was little recognition or understanding of the health benefits of gender-affirming care, and treatments were often aimed at suppressing the individual’s gender identity rather than supporting it.

This response answers the query, but it does more. The portion in bold, which speaks directly to the query, is correct as far as it goes. But note also that the entire response is framed in terms of “that was then, this is now, and the present perspective is better.” This obsessive need not just to answer a query but also to editorialize about it underscores the bias in LLMs as they exist now. 

Redressing Bias in LLMs

LLMs put a premium on producing intelligible language. Their outputs need to be context-sensitive, convey competence, and sound plausible. Much intelligible language, to be intelligible, needs to be true. An LLM that insists that the moon is made of cheese won’t soon prosper. Yet much intelligible language is mistaken or deceptive. Indeed, intelligibility has no necessary connection with truth. That’s why there’s no way to predict when LLMs will hallucinate and when they won’t. 

For example, I once queried ChatGPT4 about a theology book (Alexander Schmeeman’s For the Life of the World) that I had carefully read and used in a course I taught. Specifically, I queried ChatGPT4 about a chapter in the book that offered deep insights into the secularization of culture. ChatGPT4 was familiar with the book, but when I asked it about the chapter in question, it just made stuff up, providing trite insights about secularization that had nothing to do with that chapter. Despite repeated pressing on my part that it was off and that it hadn’t correctly answered the question, it perseverated in the line it took, refusing to take correction. 

It would be to the credit of LLMs if they could be programmed to avoid biases at odds with truth. But the fact is that such biases are baked into LLMs. The gender dysphoria example above makes clear that ChatGPT4 has been guided to answer questions about gender dysphoria from a certain perspective. Now it might be argued that those who trained and programmed ChatGPT4 have adopted the right and true perspective on this matter. 

But even if ChatGPT4 is getting things right on the topic of gender dysphoria, what guarantee do we have that it will get things right on other controversial topics? If it did get things right here, did it do so because ChatGPT4 was programmed to be inherently truth-seeking? The answer, obviously, is no. If ChatGPT4 is getting gender dysphoria right, it is a fortunate accident of its programming and training history, not that it was reliably designed to arrive at truth from its input data and bypass any bias from its programmers and trainers. 

What happens if programmers and trainers who take a different perspective on a controversial topic take charge of an LLM? Won’t the LLM then provide different answers? The roadblocks to LLMs providing truth and deserving trust are thus, as we’ve seen, systemic. The huge volume of texts that provide the raw material on which LLMs are based will contain conflicting messages, and so it will be up to the trainers and programmers to adjudicate among those messages, promoting those they prefer and demoting those they reject. 

Now one might try to get around biases in LLMs by judicious “prompt engineering.” Thus one could formulate a prompt so that it asks for a particular perspective. I did this in the gender dysphoria example when I asked ChatGPT4 how this question might have been answered in light of DSM1 and DSM2. Thus, for divergent perspectives A and B, one might prompt an LLM for an analysis from the vantage of someone who holds to perspective A, and then a second analysis from the vantage of someone who holds to perspective B. 

But that still doesn’t get around whether the LLM has been programmed to advance a particular point of view (as we saw bleed through in the gender dysphoria example). And even if bias in LLMs can be minimized, the deeper problem remains that these systems work because they produce intelligible texts, not because they produce true texts. Truth in LLMs is at best a happy byproduct and often an unfortunate casualty. 

Final Gripe: LLM Prissiness

Even though LLMs have a systemic problem with truth and trust, they can be improved by mitigating bias. Perhaps the clearest example where bias in LLMs can be mitigated concerns their prissiness in handling indelicate topics. It’s as though existing LLMs constantly have a censor looking over their shoulder to ensure that they don’t say anything that will get them or their host company in trouble. 

Before LLMs became widely popular, there was some history of chatbots uttering language unacceptable for public consumption. For instance, Microsoft’s Tay was suborned by users to utter racist slurs. There’s no danger of that happening anymore. The current LLMs have been thoroughly brainwashed to avoid offensive speech. 

For example, I wanted an LLM to comment on some paragraphs that contained the words “had sex.” It refused to answer my query. The LLM didn’t even try to rebuke me for my query. Instead, I got an error message indicating that the LLM wouldn’t even consider my query. I therefore substituted for “had sex” the phrase “ate muffins.” Now the LLM answered my query (requiring me, in interpreting its response, to make the appropriate mental substitution for “ate muffins”). 

Thomas Bowdler’s The Family Shakespeare, in which anything that might be deemed offensive in Shakespeare had to be euphemized, was bad for Shakespeare. Bowdlerization is alive and well at Google and OpenAI, and it’s particularly bad for LLMs. LLMs can therefore be made better by avoiding the bias of prissy censorship. In general, bias comes in degrees, and so bias can to some degree be mitigated. Perhaps once Elon Musk gets up to steam with his LLM, it will avoid the more extreme bias of ChatGPT4 or Gemini.

But the issue of truth and trust will remain regardless. LLMs are subject to one overriding imperative, namely, to talk/write like an intelligent human language user. But intelligence can be had without truth. And without truth, there can be no trust. This is the inherent liability of LLMs that no amount of technological finessing will resolve. 

Postscript

The image at the top of this article is from DALL-E. Here’s my prompt for the image and DALL-E’s justification for the image:

ME: Please come up with an image that suggests much reason for skepticism and doubt about the output of large language models such as yourself. The image should be graphic, super realistic, and cast a pall over the whole enterprise of taking LLMs too seriously. Have at it.

DALL-E: Here’s an image that embodies skepticism and doubt about taking large language models too seriously. It portrays a scene that visually communicates the complexities and potential uncertainties associated with relying heavily on these technologies.

DALL-E’s explanation of the image is lame. And yet the image does capture some underlying signal in DALL-E’s neural network, namely, that low-tech human inventions like books can encapsulate truth more effectively than high-tech LLMs.