Recently, design theorist Bill Dembski decided to have a go at chatbot ChatGPT4o on the question of whether 1) the existence of extraterrestrial intelligences or 2) intelligent design as the origin of our universe and life are testable ideas in science.

One must read the whole dialogue with Dembski’s interspersed commentary to get the finer points. But, as he puts it, the gist is, “one research program is regarded by the scientific mainstream as legitimate science [SETI], the other as questionable [design].”

ET just has to be Out There

A dialogue with a chatbot is, of course, a dialogue with the better-searched parts of the internet. Here are some highlights:

Me: Is SETI, the search for extraterrestrial intelligence, a testable science and, if so, what scientific claims does it make that are testable (and if so, how are they testable)?

ChatGPT4o: SETI, the Search for Extraterrestrial Intelligence, is indeed a testable science. It involves the use of scientific methods to search for evidence of intelligent life beyond Earth. Here are some key scientific claims made by SETI that are testable, along with the methods used to test them: [ChatGPT4o elaborates on the claims and testing methods, then concludes:]

SETI is a testable science that makes specific claims about the existence of extraterrestrial technological civilizations and their detectable signatures. These claims are tested through targeted observations, advanced signal processing, and the search for technosignatures. The field continues to evolve with advancements in technology and our understanding of the cosmos, making it an ongoing and dynamic area of scientific inquiry.

Bill Dembski, “The Testability of SETI and Intelligent Design According to ChatGPT4o,” June 23, 2024

Dembski goes on to ask if there is any evidence for extraterrestrial life (ET). The chatbot offers much information, then responds,

While SETI has not yet positively confirmed the existence of extraterrestrial intelligence, the search continues with increasing sophistication and sensitivity. Advances in technology and methodology hold promise for future discoveries, but as of now, the definitive evidence remains elusive.

”According to ChatGPT4o”

In other words, no. And Dembski comments,

One has to wonder if the fastidiousness of SETI researchers in looking for signs of intelligence from outer space were adopted by biologists in looking for signs of intelligence in biology, what conclusions they might reach. SETI research is like an oil company drilling for oil and never finding it. By contrast, biology is like an oil company drilling for oil and finding it over and over again, but not recognizing it as oil because Darwinism has so clouded its cognitive capacities.

”According to ChatGPT4o”

At last, the big test

Dembski asks,

Me: Is intelligent design testable?

ChatGPT4o: The question of whether Intelligent Design (ID) is testable is a subject of significant debate within the scientific community. Here’s a detailed examination of the arguments for and against the testability of Intelligent Design:

Arguments follow, and the bot concludes,

Conclusion: While proponents of Intelligent Design argue that it is testable through concepts like irreducible complexity and specified complexity, the broader scientific community generally finds these arguments insufficient. The main criticisms are that ID lacks predictive power, relies heavily on negative arguments against evolution, and implies supernatural causation, which falls outside the scope of methodological naturalism.

Ultimately, the question of testability hinges on whether ID can produce positive, predictive, and falsifiable hypotheses that can be rigorously tested and compared to naturalistic explanations. To date, the consensus in the scientific community is that Intelligent Design has not met these criteria to the extent required to be considered a testable scientific theory.

”According to ChatGPT4o”

Dembski sees this as an improvement over the all-too-typical anti-ID rant but hardly as warm as the bot’s defense of SETI. When he asks about that, the bot affirms that SETI is more testable than ID:

Conclusion: SETI fares better in regard to testability than Intelligent Design because it formulates clear, empirically testable hypotheses, operates within the framework of methodological naturalism, and produces falsifiable and reproducible results. SETI’s methodologies are well-integrated into the scientific community through peer review and transparent research practices. In contrast, Intelligent Design often lacks clear predictive power, struggles with falsifiability, and is not as well-integrated into the scientific community due to its reliance on supernatural explanations.

”According to ChatGPT4o”

Dembski comments,

This response is an exercise in special pleading, giving SETI every advantage and ID every disadvantage. By any objective standards, ID research is in a much stronger position than SETI research. ID can point to real biological systems that could plausibly be designed. To date, SETI can’t point to any effect from outer space that may plausibly be regarded as designed. The point made here about methodological naturalism is curious: if ID proponents posited a teleological force that is not mechanistically reducible and that is not supernatural, would the science of ID be thereby improved?

Is, for instance, directed panspermia, in which alien intelligences seed life on earth, a better theory of intelligent design than one whose designer might be supernatural? It is irrelevant to ID whether any designer of biological information is supernatural. Consequently, methodological naturalism is a red herring in discussions over ID.

As it is, ID research does not invoke the supernatural. It discovers patterns of information that require an intelligent cause. Such causes can work through natural processes, though that raises questions about the ultimate source of the information attributable to intelligence in nature.

”According to ChatGPT4o”

The myth of objectivity

In the end, the fundamental problem is the myth of objectivity as a guiding principle. Many people who follow science — who produce the material that the bot scarfs up and sorts — desperately want to find ET and don’t want to find design.

Here at Mind Matters News we’ve run a number of stories examining numerous theories as to why ET never shows up. Many of the same people so much reject the idea of intelligent design that they prefer to believe instead that the human mind is an illusion. Dembski can argue with a chatbot because it is probably not programmed to become profane — as so many humans have done.

However, his session with the bot suggests that at least some ID concepts are beginning to get across. A decade ago, if the bots had been around, it would all have sounded much worse.