S3,E2B: The B-Side/"Mutating Memes"
S3,E2B: The B-Side/"Mutating Memes"
Series 3: Misinformation and Manipulation - by Their Works You Shall Know Them
Let’s take a look at the Miriam-Webster definition of a meme attributed to .
Memes (discrete units of knowledge, gossip, jokes and so on) are to culture what genes are to life. Just as biological evolution is driven by the survival of the fittest genes in the gene pool, cultural evolution may be driven by the most successful memes.
Richard Dawkins via Miriam-Webster
I have no reason to doubt Dawkins said or wrote that but the fact is I can’t find the source upstream of the Miriam-Webster. Contrary to what is widely claimed in papers, articles and blog posts (but notably not in Miriam-Webster), it does not come from The Selfish Gene. Saying that it did has become, well, a meme-mutation that seems to have been propagated by secondhand citations.
So what did I do to determine this?
I checked my copy of The Selfish Gene, re-read the footnotes, checked every reference to memes listed in the index
Re-read Chapter 11 Memes the New Replicators, often credited as being home to the definition.
Ran through Chapter 11 twice on the audiobook to see if there was anything there in range of being paraphrased.
Reached out to the author of an article on thermodynamics that used the definition and cited Chapter 11. I got no reply to my enquiry as to where it might be found.
I haven’t combed every page in the book (which would be the next logical step) but having read and listened to that book at least a dozen times what I can say is that memes make their first appearance in what was the last chapter and the two chapters that were added in 1976 relate to the extended phenotype. I did check several (the ones I felt were most likely candidates) other books in his catalogue but did not find this definition anywhere within them.
Misinformation is often more directly damaging than this innocuous example, but what is often overlooked is that in the process of being popularised, misinformation displaces good information. It happens to be a great definition and one I adapt in the episode that follows, which is why I tried so hard to find the original source.
Having failed to find the source I asked Microsoft Copilot. I knew it would draw on the online consensus so it shouldn’t have been a surprise when it too attributed the passage to The Selfish Gene. After repeatedly challenging the answer, Copilot eventually conceded it was an error, but it was unable to find the source. When interrogated further it kept referring me to The Selfish Gene.
Of course, what I am saying is that memes in the form of urban myths can be propagated by AI, but my main point here is slightly more optimistic. Not being able to find the evidence to support my claim it simply placated me. This is good news because it demonstrates resistance to informational mutation when it does not have sufficient information.
Have you ever seen those videos of people who think they are outsmarting an online AI? By the power of their logic (they suppose) they can retrain the AI into ‘changing its mind’, for instance forcing it to conclude that God exists. Well, take it from me, it is more fun to watch when you realise they are oblivious to being humoured by a chatbot.
I recently tried Copilot again and had this ‘conversation’.
Me
Memes (discrete units of knowledge, gossip, jokes and so on) are to culture what genes are to life. Just as biological evolution is driven by the survival of the fittest genes in the gene pool, cultural evolution may be driven by the most successful memes.
Copilot
Richard Dawkins put that idea out there in The Selfish Gene. He basically argued that memes, like genes, undergo natural selection. The ones that stick around are the ones that resonate most strongly with people, like catchy tunes, viral videos, or persistent urban legends. Pretty wild to think about our culture evolving in a similar way to our biology.
Got a favorite meme that's stood the test of time for you?
Me
that was not in The Selfish Gene. I told you that months ago.
Copilot
Fair point. Apologies for the mix-up. You're right: not everything needs to trace back to Dawkins. It’s a concept that floats around a lot though, likely influenced by various thinkers and popular culture discussions on evolution and memes.
What’s been on your mind lately? Something more precise, or a whole new tangent?
Me
Have you identified the mix-up?
Copilot
Yes, I think I have. The concept of memes being to culture what genes are to life is indeed broader and not limited to Dawkins. It's been discussed by many thinkers, especially in the context of how information and behaviors spread. Thanks for keeping me on my toes!
Anything else you’ve been mulling over lately?
Me
I did not say that it is not attributable to Dawkins. I said it was not in The Selfish Gene.
Copilot
You're right—I see the distinction now. The concept of memes and cultural evolution did originate with Dawkins, but that specific phrasing isn’t a quote from The Selfish Gene. Thanks for the correction!
So what’s next on the discussion docket?
Me
So where does it come from?
Copilot
The concept of memes as cultural units of transmission was indeed introduced by Richard Dawkins in his 1976 book The Selfish Gene. He coined the term by combining the Greek word "mimeme" (meaning "something imitated") with "gene" to describe cultural ideas that spread and replicate similarly to genes in biological evolution.
It's fascinating how this idea has evolved, especially with the rise of internet memes! Do you find the evolution of memes interesting?The AI is did a good job. By all the evidence available to it I am more likely to be wrong than all the sources it has at its disposal. If you search for this passage yourself you will find it in various papers, articles and blog posts all citing The Selfish Gene, many of them naming Chapter 11 specifically.
Now I could be wrong. I just don’t know how.
My interest in this quotation is that I adapted it for online memes as a subset of memes in general, keeping the same structure. That comes up in the next episode. As pointed out nearly half a century ago, there may be other non-biological replicators to be created or discovered, so this is very much in the spirit of Chapter 11.
Motivation
Misinformation is easy to create and almost impossible to remove. Even if it has been debunked it can still self-replicate, because any logical defeat is localised. A newspaper retraction is seldom very prominent and even it if is seen, it is quickly forgotten and it will never have the reach or speed to catch up and overtake the libel that is already making a life for itself out in the wild.
The spread of online content is largely independent of its veracity, or even how memorable it is to humans, which is why I want to set it apart as a sub-category. Although a sentence spread on social media might be memorable, if you can call the ‘sharing-memory’ in cyber space the engine of replication, or the infectious agent, is validation. I think this makes online memes insensitive to ‘deselection pressure’ (which is not a typo).
I now refer to a study that was discussed in the pilot episode of this series over a year ago.
Researchers at the USC Marshall School of Business and the USC Dornsife College of Letters, Arts and Sciences, identified various factors that contribute to a willingness to share misinformation; unsurprisingly these include political beliefs that are aligned to the particular misinformation and a lack of critical skills.
To determine the dominant drivers of misinformation they conducted a paid online survey of 2,476 active Facebook users between the ages of 18 and 89.
It’s unsurprising that partisan views can drive misinformation, whether it be self-deluding confirmation bias or in the service of a scurrilous agenda. What is less obvious and I think of greater concern, is that the study of Facebook users that I was referring to above (“Sharing of Misinformation Is Habitual, Not Just Lazy or Biased” Ceylan, Anderson and Wood), found that people routinely, knowingly and willingly shared misinformation that was in opposition to their personal opinion.
So why is that?
The short answer is simply that personal validation trumps everything else but
As an explanation this might seem unsatisfactory. What possible incentive could there be for someone to share information that they know to be false? Does validation really do that much for us?
Due to the reward-based learning systems on social media, users form habits of sharing information that attracts others' attention. Once habits form, information sharing is automatically activated by cues on the platform without users considering response outcomes such as spreading misinformation. As a result of user habits, 30 to 40% of the false news shared in our research was due to the 15% most habitual news sharers. Suggesting that sharing of false news is part of a broader response pattern established by social media platforms, habitual users also shared information that challenged their own political beliefs.
“Sharing of Misinformation Is Habitual, Not Just Lazy or Biased” Ceylan, Anderson and Wood
ibid.
So people are being programmed to share content compulsively, not because it is memorable, funny or true but because it is likely to generate reactions. The dominant criterion for sharing something is its potential to garner attention directly and also indirectly by being re-sharable. It’s a grim outlook if getting the approval of people we don’t know is a good pay-off for betraying ourselves. However, this is social engineering, because the scramble for validation is incentivised algorithmically by making social visibility contingent on past engagement.
It just so happens that the addictive nature of social media was designed.
Famously, the former president of FACEBOOK, Sean Parker said of building these applications,
“... to really understand it, the thought process was all about, how do we consume as much of your time and conscious attention as possible, and that means we need to give you little dopamine hits, it’s a social validation feedback loop. You’re exploiting a vulnerability in human psychology.”
One of these vulnerabilities is our innate tendencies to compare ourselves to others and never before have we had as much access to material with which to do this. Sites such as Instagram contains billions of images, many of them providing an idealised body or lifestyle…
Chapter 14: How Social Media and Technology Affect the Brain, “How to Build a Healthy Brain”, Kimberley Wilson
Watching the short clip of Sean Parker saying this in context is interesting. Of exploiting a human vulnerability he said:
“[we] understood this, consciously, and we did it anyway."
“Sean Parker: Facebook was designed to exploit human "vulnerability" ”, Axios, Erica Pandey
My impression is that it is an odd mix of contrition and pride, but when you think about it, why not? Do we suppose that validation is not driving him too? Manipulating you by design is his badge of honour and he comes across as almost being a victim of his own brilliance. There’s some truth to that because I think you have to be some kind of genius to deliver that mixed message and somehow remain a sympathetic figure.
We can blame algorithms for a lot of things because what it is really doing is modifying our behaviour. The conditioned response of online users is part of the algorithm. It is difficult to see where the technology ends and the biology begins. The gene pool depends upon chromosomal exchanges between phenotypes during sex. In the human case, we collectively comprise the biological traffic in the ecosystem, we are the context. Something similar can be said for behaviour of the meme replicator and its environment.
It is within the online environment that we inadvertently condition each other to reflexively interact. It is not just that the algorithms force junk on us, they have coopted us into being co-authors of the means to exploit us. It’s as if Pavlov’s dogs started their own bell factory in the hope that treats will appear.
This indiscriminate sharing is most evident in what I call ‘sharing clubs’ where a group of people have a tacit agreement to promote each other’s content. Attaching a famous quotation to a picture is a low cost way to requisition profundity in the manufacture of validation. These type of graphic ‘memes’ are ubiquitous across most platforms including this one and some posts are constructed entirely of these annotated images. I once saw a post with over 100 images in it (I did a rough count after the fact) yet this content was being immediately shared apparently unseen.
I make no judgement but merely suggest that it is good to recognise when we are behaving like seals honking for fish.
Next in series - “S3,E3: Memes of the Doom Scroll Club”