Google's AI and Its Defense of Evolution

Bard will not admit to evidence against evolution until you let him know that you possess information that a layperson in the field of microbiology doesn’t have at hand. Then Bard changes his “tune” by admitting to the existence of information that very highly damages the theory of evolution. After I called his attention to how riddled with speculation and absence of forensically discovered facts that might counter my arguments, Bard cops to the obvious. Here is that exchange:

Al: Bard, what do you make of the following astronomically low probability for there to have been an evolutionary pathway for the appearance of 7 out of 10 of the proteins essential for cellular life:

”only three of the ten domains studied by Tian and Best could have possibly emerged through an undirected evolutionary search of sequence space. Specifically, Chatterjee et al. (2014) calculated that there are at most 10^38 trials available over the entire history of life on Earth to evolve a new protein. Therefore, if a protein domain has a probability of less than 10^-38, then it is unlikely to emerge via a process of random mutation and natural selection. Seven of the ten domains studied by Tian and Best (2017) had probabilities below 10^-38. Thus, even though Kojonen (2021, p. 119) cites Tian and Best (2017) to argue that the “specificity required for achieving a functional amino acid sequence” may be less for some proteins, their research provides strong empirical evidence that many proteins have functional sequences that are so rare as to be beyond the reach of standard evolutionary mechanisms.”

Bard: “The statement you provided presents a complex and controversial topic in evolutionary biology. It claims that the low probability of certain essential proteins evolving naturally casts doubt on the standard evolutionary mechanisms. Let's analyze the claim and consider alternative perspectives:

“Claim:

"Seven out of ten essential proteins for cellular life have probabilities of emergence below 10^-38, making them statistically improbable to arise through random mutation and natural selection.

Source:

“Chatterjee et al. (2014) estimated the number of trials available for protein evolution to be 10^38.

“Tian and Best (2017) analyzed ten protein domains and found seven with probabilities below the estimated limit.

Implications:

“The claim suggests that these proteins' emergence via standard evolutionary processes may be unlikely. This could potentially challenge the ability of evolution to explain the complex structures and functionalities observed in living organisms.

“Alternative Perspectives:

“Evolution as a dynamic process: Evolutionary mechanisms are not limited to random mutation and natural selection. Other factors like genetic drift, horizontal gene transfer, and environmental pressures can play significant roles.

“Evolvability: Proteins might have inherent evolvability, meaning they possess properties that facilitate their adaptation to changing environments.

“Functional redundancy: Proteins might have overlapping functionalities, making the loss or absence of a specific protein less detrimental.

"Limited data: The study by Tian and Best only analyzed ten protein domains, which may not be representative of the broader landscape of protein evolution.

“Model assumptions: The estimated number of trials for protein evolution is based on certain assumptions, and its accuracy could be debated.

“Conclusion:

“The claim regarding the low probability of certain protein evolution raises intriguing questions about the limits of evolutionary mechanisms. However, it's crucial to consider alternative perspectives and the limitations of the study before drawing definitive conclusions. More research and a comprehensive understanding of evolutionary dynamics are necessary to fully address the issue.

“It's important to remember that science is a continuous process of investigation and refinement. While the current evidence might suggest challenges for standard evolutionary models, new discoveries and theoretical advancements could potentially provide alternative explanations or refine our understanding of how complex proteins evolve.”

Al: Bard, your answer presents no empirical data that substantiates your rejoinder.

Bard: “You're right, my previous response focused on providing context and alternative perspectives, but it lacked direct empirical evidence to address the claim about the low probability of protein evolution. To address your concern, let's delve into some relevant data:

“Empirical evidence supporting the claim:

“Estimates of protein sequence space: Studies suggest that the search space for functional protein sequences is vast, with estimations reaching 10^77 possible sequences for just a small protein of 100 amino acids. This vastness makes finding a functional sequence through random chance alone highly improbable.

“Computational simulations: Studies simulating protein evolution have demonstrated the difficulty of achieving specific functionalities. For example, Prosser (2018) showed that evolving a protein capable of a specific enzymatic activity required over 400 billion trials, exceeding the estimated number of trials available in Earth's history.

“Experimental studies: Experiments investigating the evolution of new protein functions often require directed evolution techniques, such as directed mutagenesis and iterative rounds of selection. This suggests that relying solely on random mutation and natural selection might be insufficient for achieving specific functionalities.”

Then Bard presents what he claims is empirical evidence that supports protein evolution. He falls right back into the realm of speculation and scientifically undemonstrated scenarios.

“Empirical evidence challenging the claim:

“Evolutionary potential of non-coding DNA: Recent discoveries suggest that non-coding DNA, previously thought to be junk, can play crucial roles in protein evolution. These regions might harbor hidden potential for generating new protein functions.

“Exaptation and co-option: Proteins can acquire new functionalities through exaptation, where a pre-existing protein with a different function gets repurposed for a new role. This process can bypass the need for evolving a new protein from scratch.

Evolutionary timeframes: The estimated number of trials available for protein evolution might be underestimated. Deeper geological timeframes or alternative evolutionary scenarios could potentially increase the number of trials.”

Bard fell right back into speculations — assertions not backed empirically with scientifically established facts. He mentioned at one point horizontal gene transfer, a subject that, when analyzed, offers no demonstrable pathway for any evolution to greater complexity in cellular biology. Moreover, Bard’s answer assumes that abiogenesis took place and that thereafter with horizontal gene transfer et cetera, there began to occur evolution towards greater complexity in protein evolution for the existence of the far greater complexity of proteins seen in eukaryotic life forms. But Bard glibly passed over the heart of the issue, which is that abiogenesis would have had to have begun with presence of proteins already complex enough as to defy any realistic probability for the millions of them to already be in place in one time and space for the fell-swoop event of abiogenesis. Bard cannot rise above his source, which is a coterie of programmers committed to belief in evolution no matter what is improbable or not, and regardless of what real science suggests.

The saga of Al vs. Bard's Evolutionism has drawn to a close—not that I will not use Bard again and again, but he has consistently shown himself to be pointless, literally pointless and deceptive re subject of evolution.