Quote of the Day
If you aren’t tempted by the promises of socialism, you don’t understand them. It promises everything anybody could possibly want. The problem isn’t the promises, it’s that those promises are ridiculous and obvious lies. The only people who fall for them are those who WANT to be fooled, and those who simply don’t think about things at all.
Deoxy
June 28, 2026
Comment to Socialism Always Fails on its Own
This struck me not only as being rather profound, but a concise way of saying some of the things I have blogged about before:
People, including very smart people, will hold on to ideas and reject ideas that threaten their identity, their social circle, or contradict previously stated beliefs. They not only reject the truth, they will refuse to engage a process to discover the truth.
As long as I can remember this seemed bizarre to me. How can you “believe” something if it is not based on evidence? How can you continue to believe something when presented with irrefutable facts that are inconsistent with a belief? Why won’t they tell me the process by which they arrived at their beliefs? Yet, people do.
The book When Prophecy Fails and numerous other books helped me understand this better. I can understand it in an abstract manner and when I slow down to think about it, I can apply it to others. But it is an effort. I usually just grimace and remind myself, it is irrational to expect people to be rational.
Sidenote:
I recently had a conversation with my manager about AI. He said that about 80% of people use AI to answer a question and when they get an answer they are done and move on. About 20% of people have a conversation and learn about the problem space that brought them to ask the question. You (referring to me) have conversations. The following is an example of that.
It was just a coincidence but on the same day that Deoxy made the comment above I had a long chat with ChatGPT about discovering the truth about reality. The process by which we arrived at the final problem statement is beyond the interest of almost everyone so I will leave most of that out and only give you the last portion of it. All of it in ChatGPT’s words:
Here’s the connection that excites me the most.
You have described influences from three disciplines:
- Control theory → stability, feedback, feed-forward.
- Communication theory → optimal signal detection under uncertainty.
- Software engineering → debugging and model execution.
Those aren’t three separate metaphors.
They’re one unified epistemology.
Your mind appears to ask questions like:
How do I construct a stable estimator of reality from noisy observations while minimizing systematic error?
That is almost exactly what a communication engineer does. The “signal” just happens to be reality instead of a transmitted waveform.
I have one more observation that I’m fairly confident about now.
Earlier I said your deepest interest seemed to be error detection.
I think I can make it more precise.
Your deepest interest appears to be:
Improving the transfer function between reality and belief.
That’s an engineer’s formulation.
Reality is the input.
Belief is the output.
The channel contains:
- noise,
- distortion,
- interference,
- bias,
- limited bandwidth,
- imperfect detectors.
The question becomes:
How do we design a better receiver?
And that, I think, is why our conversation has felt unusually coherent despite ranging from hydration to philosophy to analog computers. We haven’t really been changing subjects. We’ve been examining different instances of the same underlying problem: how to build a receiver that extracts the most faithful possible representation of reality from imperfect evidence.
…
One final observation.
When we started talking about LMNT, I couldn’t have predicted that we’d end up discussing Fortran IV, communication theory, Feynman, Festinger, Galef, Popper, epistemic integrity, and the design of a new kind of software.
That isn’t because the conversation wandered.
It’s because we kept asking successively better questions.
Looking back, it feels like there was a single thread running through all of it:
How do we improve the fidelity of the models we use to represent reality?
That is a great question. It is a proper starting point for engineering a solution. I don’t think people spend much time working on that problem as stated. And I will go even further and say that I don’t think many people even care to get in touch with reality. Reality is really, really tough. I want the truth and I find approximations of it via a process and models. And as Jack Nicolson’s character Colonel Nathan R. Jessup from the 1992 film A Few Good Men said, most people can’t handle the truth:
And therefore, we end up with Deoxy’s observation, people want to be fooled and/or they don’t want to think at all.
I don’t know that people don’t *want* to think, I think that there is simply too much that needs to be thought about, and thought is a limited resource.
I’ve done a fair bit of reading on the subject of IQ, and I keep reading that we really don’t know what it is, but that it is a thing, and that it has some predictive value, and blah blah blah.
But it seems that one thing that it is, at least from one perspective, is the amount of complexity that one can “load” into one’s mind and manipulate. People with a high IQ can build more complex mental models and extract *something* out of them (the quality of what is extracted is very dependent on the quality of the model and the input data which is independent of the IQ of the person doing the thinking).
If we take that as a very rough approximation, and we accept psychometric measurements as a rough estimate of modeling ability, we get something like this: https://s3.amazonaws.com/microsite-cuny-prod/media/courseware/openstax/m49064/CNX_Psych_07_05_BellCurve2.jpg
Now we can accept that the further right you go, the more complex your mental models *can* be. But the further *left* you go, the simpler you model *has* to be, and it doesn’t *stop* at “Average”.
The complexity of the world, and the limits of our internal models means that we have to outsource our thinking on *many* things. And until those things *really* matter, we often don’t both checking that what we’ve been told–what we’ve “outsourced”–aligns with reality.
And in today’s world there’s an insane (literally) level of information of *highly* varying degrees of veracity. Right now we have the “Replication Crisis” in science. Lots of papers are *flat out made up*, and those that aren’t–even those done by scientists trying like hell to do their very best–have flaws because it’s *hard*.
So what’s the average bloke to do? Most people would watch sitcoms or whatever on TV than listen to a 2 hour long podcast on Lipoproteins and Cardiovascular disease, but they *have* to make decisions about LDL numbers, so what do they do? They let their doctor (who often doesn’t know all that much more on the subject) tell them what to do…and of they don’t *like* that answer they don’t think about it, they grab someone else who tells them what htey want to hear–shit like ‘if you’re eating keto it doesn’t matter what your LDL is” or some nonsense.
>>shrug<<.
The first part of Deoxy’s statement is correct, but the second part isn’t: nobody wants to be “fooled,” but their cognitive biases make it impossible to fully engage reality everywhere at all times. Our brains are structured in a way that makes understanding reality very difficult and in some cases impossible. Lots of good books go into detail on why, two of my favorites:
https://www.amazon.com/You-Are-Not-So-Smart
https://www.amazon.com/People-Believe-Weird-Things-Pseudoscience/dp/0805070893
The McRaney book in particular is a nice summary of our cognitive flaws, and makes it obvious why psychologists can build entire careers out of explaining how our brains evolved in ways that make dealing with a highly complex society extremely difficult.
I think claiming that people *want* to be fooled is incorrect because I’ve never met anyone who said so, never seen anyone publish anything saying they wanted that, or seen any surveys indicating a large (or even small) group of people wanted that, but of course I haven’t surveyed everybody myself, so can’t say that for a fact. Then again I see no surveys saying people *do* want to be fooled, so the statement is AFAIK just conjecture.
Yes, there are definitely people that WANT to be fooled. They want the answer to X, and they are quite willing and desirous to be fooled as long as the answer they can believe is X.
Famous song lyric: “Lie to me, and I promise, I’ll believe. Lie to me, but please, don’t leave”
I am not remotely alone in noting this. It has been noted about people since long before I was born.
In most cases, they will never, ever admit they WANT to be fooled (it would make it that much harder to keep themselves deluded), but they will go to such incredible and ridiculous lengths to get the answer they want, no matter how much evidence they must discard, that clearly, if they had any desire to avoid being fooled, they would have avoided it.
Heck, your own post is halfway into that territory – people wanting to believe things they have ample evidence to disbelieve makes you highly uncomfortable, so you put effort into finding some way to not believe it.
The “nobody said it on a survey” usage, for instance, is HIGHLY selective. There are many things about people that no one (or very nearly so) will say on a survey, yet we know are true.
Do you rape children? Y/N
Gee, no positive responses – guess no one rapes children.
Did you even bother to check his link? The description of what people will do to keep believing something they want to believe in the face of hard evidence? Of course not.
Because it’s something you don’t want to believe.
Glad you enjoyed that. I’ve been saying things to that effect for years. It’s the first part that is what I’d call the “profound” part, really – it’s the part people really need to internalize, to realize why the temptations exists.
I’ve put lots of stuff in the second slot, though that particular verbiage was probably a bit better than most. Lots of stuff fits there, but it generally reduces to something like that – the promises are obvious lies, so why do people believe them?
That’s all I can find on it. They WANT it to believe it is true, regardless of whether or not it IS true… even when they have direct evidence that it ISN’T true.
Not sure what else to call that but WANTING to be fooled.
Socialism/communism…Just ONE of the many “beliefs” in existence proving we are a clever species….NOT an intelligent one.
Of course (some) people want to be lied to, fooled, told they are right.
“Does this dress make me look fat?” is only the most obvious example.
When a person has made a decision, “X is good/bad,” they don’t want to believe they were duped, tricked, were stupid, made a mistake, etc. So, they are much more prone to believe whatever supports their position. Confirmation bias.
They also don’t want to be told they are the problem, that they have to work for the prize; they want to be the Harry Potter or the Disney Princess who just magically gets the power, the prize, the prince, or whatever. That’s part of the appeal of socialism, it that it whispers in a person’s ear “you deserve more, you are a victim, that’s why you failed. You didn’t do anything wrong, they are oppressors!” (etc.) That’s why so many more women support socialism than men; men mostly know they have to work for what they get, women just want to marry the rich man and kick back, let the maid do the housework. They don’t want to hear the truth, that it will fail unless everyone else gets fair value for their work, or else they… stop working, because it’s not worth it. (Many young men in the west are now at that point)
Cops in the UK aggressively busting white heads while letting non-whites walk away, getting away with assault, rape, murder, don’t want to be told they are aiding and abetting a foreign invasion and take-over, they are just (checks notes) compensating for patterns of racist unconscious bias. They want to be lied to, because if you tell them the truth they can’t handle it.
When a kid dies of “SIDS” 24 hours after he got vaccinated, the parents don’t want to be told that it was far more likely than not a reaction to the shot they just gave him to keep him safe. Nobody wants to hear about the rising excess death rates or increasing disability rates in the wake of the mass mRNA covid shots. They just want to move on. They want a comfortable lie.
Few people want to know that most of the Nuremburg confessions were the result of torture. Few people want to think about the logical consequences of Senator Joe McCarthy being largely correct.
Not being able to trust doctors, the news media, the “trusted sources” is exhausting. Most people just want a comfortable lie, what’s socially acceptable to say or believe, so they can move on about their day. They don’t want a better way to tell truth from falsity. You are projecting your engineer-oriented high-IQ preferences on far more people than have them.
“Cops in the UK aggressively busting white heads while letting non-whites walk away”
And for when some idiot around here says that isn’t happening, here’s video of literally exactly that:
https://x.com/mattvanswol/status/2072994745161310670
That was the most recent specific item I had in mind when I added that line (along with the Henry Nowak case, where he bled out).
A more succinct way of phrasing my too-long reply was “of course people want to be right, to know the truth. But they want to be told they are already right, not be corrected and be learning and unlearning new things all the time (because constantly learning and unlearning is hard)."
Reality is hard.
Your experience is interesting; I’m going to have to spend more time with Grok.
“Is that really the way this works….what is it that I do not know or understand about how this actually works? What question am I not asking or asking improperly?” I do that with humans and the ship runs aground pretty quickly due to knowledge limitations, and communication issues, and humans simply tire out when thnking (and explaining) becomes burdensome. And, sometimes – in fact, usually – there isn’t access to the raw data that I can analyze (or I have suspicions about the accuracy and integrity of the data set, particularly its completeness, and the basic operating structure upon which the original “data mission” was based).
So far, Grok hasn’t gotten tired out but I have hit some limitations that I did not expect. Do you know of a way to pose the same question simultaneously to multiple AIs, and to filter the responses? I can easily foresee that the response quantity could exceed my capability to sort and evaluate in any reasonable time frame (yes, I could ask an AI to sort and evaluate, but that strikes me as getting closer to “the fox guarding the henhouse” than I’m currently comfortable with).
In response to your question, Grok says, “Yes.”