“Why humans cling to stories”

I prompted Perplexity to look for themes or trends in the 70+ posts (going back to 2004) in the Religion category.


1. Religion as human-made stories and systems

You treat religion less as revelation and more as a **human** technology: something people invent, edit, and use to organize behavior, power, and meaning. You’re drawn to writers like Harari, Adams, Hines, Watts, Harris, and Ehrman who frame gods, money, nations, and ideologies as “shared fictions” or “maps” that work pragmatically rather than metaphysically. Your own comments echo that: religion is one example of a larger human habit of myth‑making to hold fragile social orders together.

2. Skepticism of certainty, affection for “I don’t know”

Many posts poke at people who are utterly sure they’ve found the “one true faith” out of thousands of incompatible options. You highlight quotes and essays that argue the only honest stance is some version of “I don’t know, and neither do you,” and you clearly resonate with that. The tone is rarely angry; it’s closer to amused disbelief at how confident people can be in claims they can’t possibly verify.

3. Religion, ego, and performance

You repeatedly connect religiosity to **ego**: chosen peoples, special relationships with God, and the need to feel correct or favored. Posts about appearing religious (Machiavelli, “appearing to be religious”), evangelical branding, and “religion and ego” all treat belief as something performed for social and psychological payoff as much as for doctrine. You’re especially interested in the gap between what people say they believe and how they actually behave or legislate.

4. Power, politics, and “weaponized” faith

Another through‑line is religion as a power tool: surveillance, social control, justification for violence, or political branding (evangelicals and the GOP, Christian Right decline, cults, “The Family”). You focus less on abstract theology and more on who gets to define “God’s will” and what that does in the real world. Organized religion, in your posts, is often less about God than about those who act in his name.

5. Spirituality without dogma

Alongside the critique, there’s a consistent interest in non‑dogmatic spirituality: Zen, Buddhism, meditation, Sam Harris’s “spirituality without religion,” Alan Watts on stillness and consciousness. You repeatedly highlight ideas about awareness, present‑moment experience, the illusory self, and consciousness as primary, often contrasting that with inherited belief systems and scriptures “cobbled together during the Iron Age.” You seem much more attracted to practices that clarify experience than to creeds that explain it.

6. Religion, technology, and future “gods”

In more recent posts you connect religion to AI, Silicon Valley, and new ideologies: AI‑written scriptures, Silicon Valley as a birthplace of future religions, money and the economy as a kind of religion, liberalism/communism/nationalism as modern creeds. A recurring question is what happens to “religions of text” when the texts start talking, or when algorithms and biotech become the new sources of superhuman authority.

7. Your overall stance

Putting it all together, your “religion posts” read less like attacks on believers and more like a long, curious investigation into why humans cling to stories and what those stories do to us. You tend to trust awareness over belief, experience over doctrine, and are wary whenever any story—religious or secular—claims unquestionable authority.

Tag cloud graphic

An earlier post featured two graphical representations (from Perplexity) of the categories I’m currently using on smays.com. As a follow-up, I uploaded the current list of tags.

At first glance one would think this blog is just about ChatGPT and it did capture a lot of my attention over the past couple of years. That will change now that I have deleted my ChatGPT account.

During recent blog maintenance, I moved ChatGPT from category to tag (along with Perplexity and Gemini). Artificial Intelligence is the top-level category for those topics (link below).

Along with all of the blog posts on this topic, I saved a lot of those conversations to my local Documents folder. This morning I prompted Gemini to analyze that “AI Bots” folder. Continue reading

Crime Fiction Philosphy

The #1 reason I started this blog was to have a place I could save (and later find) stuff. Lines from movies, favorite quotes from books, a photo, etc. Additionally, I save stuff in a folder in the cloud. AI tools like Gemini offer interesting and creative ways to look at these archives. Below are ten quotes of a philosophical nature from Crime Fiction novels I’ve read.


  1. “The memory is like twin orbiting stars, one visible, one dark, the trajectory of what’s evident forever affected by the gravity of what’s concealed.” — “O” Is for Outlaw, Sue Grafton
  2. “Integrity is not a conditional word. It doesn’t blow in the wind or change with the weather. It is your inner image of yourself, and if you look in there and see a man who won’t cheat, then you know he never will.” — A Deadly Shade of Gold, John D. MacDonald
  3. “Civilization seems to be something we choose when it fits our purpose.” — A Drink Before the War, Dennis Lehane
  4. “Hypocrisy is the tribute that vice pays to virtue, dear man.” — A Murder of Quality, John le Carré
  5. “Sometimes it’s a dog-eat-dog world and the rest of the time it’s the other way around.” — A Dance at the Slaughterhouse, Lawrence Block
  6. “The whole legal system—if you think it’s just a big set of rules, you’re dead wrong. It’s really a bunch of people sitting around and talking to each other, deciding what they want to do with you.” — A Cold Day in Paradise, Steve Hamilton
  7. “Real power around the world does not reside with governments any longer, but with private interests. Real power is secret power.” — A Firing Offense, David Ignatius
  8. “I believe in God, but not as a he or she or an it, but as something that defines my ability to conceptualize within the rather paltry frames of reference I have on hand.” — A Drink Before the War, Dennis Lehane
  9. “Education is something which should be apart from the necessities of earning a living… the measured and guided study of the history of man’s reiteration of the most agonizing question of all: Why?” — A Deadly Shade of Gold, John D. MacDonald
  10. “Even our most arbitrary actions are the result of the trips we take down our mental highways.” — A Little Yellow Dog, Walter Mosley

Pretty sure my list would have been different but I see that as a feature, not a bug.

I deleted my ChatGPT account today

[click through to post to see comment/update]

I’ve been playing with ChatGPT for more than two years. I’ve shared a bunch (143) of those “conversations” here. Initially, I planned to drop back from the $20 a month Pro plan to the free version. But decided to go nuclear.

I’ve been using Perplexity more and find Google’s Gemini as good or better than ChatGPT. But the tipping point was probably OpenAI’s decision to start selling ads on their low-end plans. The other AI companies might follow suit and I’ll probably ditch them if and when.

Anthropic (the company behind Claude) is having some fun with this in an ad that will run during Sunday’s Super Bowl. (Watch on YouTube)

The company says there are several dangers with including ads in chatbot conversations, including potential bias and incentivizing chatbots to keep users in conversations for longer periods.

Consider a concrete example. A user mentions they’re having trouble sleeping. An assistant without advertising incentives would explore the various potential causes—stress, environment, habits, and so on—based on what might be most insightful to the user. An ad-supported assistant has an additional consideration: whether the conversation presents an opportunity to make a transaction […]

Such ads would also introduce an incentive to optimize for engagement—for the amount of time people spend using Claude and how often they return. These metrics aren’t necessarily aligned with being genuinely helpful. The most useful AI interaction might be a short one, or one that resolves the user’s request without prompting further conversation.

So, you ask, are you going to stop using LLM’s all together? Doubtful. They’re just too useful. And the technology is going to be everywhere. (see my previous post on The Agentic iPhone)

If these AI tools had been around in 2002 when I started this blog, it would be a very different creature today. They know more and they write better. Maybe it’s like long division or cursive writing. I worked to hard to learn those skills and I’d hate to lose them. Don’t want some AI writing my blog even if it’s better at it. And, yes, Gemini and Perplexity get mentioned here frequently so torching ChatGPT is mostly symbolic.

The agentic iPhone

Last month Apple announced a partnership with Google that will mark a fundamental shift in the iPhone architecture. The integration of Gemini into iOS means the system is pivoting from a collection of apps to an agentic operating system. It turns the iPhone into a more powerful cognitive lever, but it demands you trust the “black box” more than ever before. I prompted Gemini to show me what that might look like. Excerpts below, the full thread here)

I asked how a new, more powerful iPhone might change the way I write or research my blog posts:


When the operating system moves from being a “file cabinet” to an “active participant,” the boundary between your thoughts and the machine’s suggestions begins to blur.

  • The Loss of Serendipity: When the AI “fetches” the exact answer, you miss the accidental discovery of a different, unrelated factoid in the “wrong” folder. The “digital twin” optimizes for efficiency, but creativity often thrives on inefficiency.
  • The Echo Chamber of One: If Gemini is trained on your “Personal Context,” it will get very good at sounding like you. There is a real risk that your blog posts will start to feel like they’ve been “laundered” through an AI that is simply reflecting your own style back at you, stripping away the rough edges of original thought.
  • The “Privacy vs. Utility” Trap: To get these benefits, you have to let the “Campos” agent index your “private thoughts.” You’re essentially trading the sanctity of your “unrecorded” mind for a more powerful cognitive lever.

I’m sure I’ll find some uses for the new iOS but writing my blog posts won’t be one of them. Near the end of the thread Gemini gives specific instructions for how to disable some of these features.

Gemini analysis of my taste in movies

(Gemini) MovieLens.org is a non-commercial movie recommendation engine and research platform operated by the GroupLens Research lab at the University of Minnesota. Since its launch in 1997, it has served a dual purpose: providing users with high-accuracy personalized film suggestions and serving as a critical “living laboratory” for the study of collaborative filtering and human-computer interaction.

Unlike commercial alternatives like IMDb or Letterboxd, MovieLens is entirely free of advertisements and corporate sponsorship. Its primary output is academic insight. The site is famous for pioneering early collaborative filtering algorithms which predict how you will rate a film based on your historical behavior and the behavior of similar users.

Last year I spent a few hours on MovieLens.org rating 435 movies I had watched. I think my criteria was “would I watch this movie again?” I uploaded those those movies and my ratings and asked Gemini for an analysis.


Based on your 435 ratings, I’ve performed a skeptical audit of your cinematic preferences. I’ve bypassed the “predictive recommendations” fluff to look at where your taste actually diverges from the consensus.

1. The “Lebowski” Anomaly (Contrarian Profile) -You are significantly more critical than the average MovieLens user. While the site average is ~3.72, your mean rating is 3.41. You are most “contrarian” when it comes to established cult classics and high-concept stylistic films.

  • The Big Lebowski (1998): You gave this a 1.0, while the average is 3.99. This is a massive 3-point delta.
  • The Hateful Eight (2015): You gave it a 1.0 (Avg: 3.89).
  • The Abyss (1989): You gave it a 1.0 (Avg: 3.68).
  • Scott Pilgrim vs. the World (2010): You gave it a 1.5 (Avg: 3.77).

Analysis: You appear to have a low tolerance for “quirk” or indulgent stylistic flourishes that others label as “genius.”

2. The “Maverick” Picks (Guilty Pleasures or Hidden Gems?) – Conversely, you value certain films far higher than the general public. Your “Maverick” score is highest for:

  • Duets (2000): You gave it a 5.0 (Avg: 2.85). This is your largest positive divergence (+2.15).
  • World War Z (2013): You gave it a 5.0 (Avg: 3.30).
  • The Bourne Legacy (2012): You gave it a 5.0 (Avg: 3.43).
  • Mosul (2019): You gave it a 5.0 (Avg: 3.52).

Analysis: You seem to favor competence and high-stakes procedural/action narratives (Mosul, Bourne, Sicario) over “vibe-based” cinema.

3. Historical Bias (Decade Analysis) – Despite your skeptical leanings, you have a soft spot for the mid-century.

  • 1950s: Your highest-rated decade (Avg: 3.80).
  • 2010s: Your most critical decade (Avg: 3.30).
  • 1990s: Where you spent the most time (100 movies rated).

4. Interest Alignment: Radio & Mechanics – Given your interest in radio history and mechanical vehicles:

  • Radio: You gave Broadcast News (1987) a perfect 5.0. You seem to appreciate the “transmission” of truth or the mechanics of the medium.
  • Mechanical/Procedural: You rated Sicario (2015) a 5.0, which aligns with your preference for technical precision and unsentimental realism.
  • Consciousness/Mind: You gave A Beautiful Mind (2001) a 2.0, suggesting a skepticism toward Hollywood’s “glossy” portrayal of cognitive struggles.

You are a Pragmatic Realist. You reward movies that execute a specific function well (thrillers, procedurals, mid-century classics) and punitively down-rate movies that rely on irony, surrealism, or “cult” status to earn their keep.


Hmm. Not sure I agree but I guess the data doesn’t lie.

“Can AI help us find God?”

Religious knowledge has become easy to access with as much detail as you might wish. You can learn about Vatican II or the Talmud ad infinitum. But it may mean something different to practitioners when it does not come from another human. An AI can write a sermon; in fact, if some confessional accounts can be believed, a majority of sermons are now at least co-authored with AI. But can it deliver that sermon and move worshippers to go out and do good works? With where things stand now, I doubt it.

From Tyler Cowen’s blog

Self, Universe, and Gibson’s Peripheral

As part of my on-going test drive of Google’s Gemini, I uploaded my 77 blog posts tagged Self and 51 posts tagged Universe with the following prompt:

I’d like to discuss “the nature of The Universe” as it relates to the Self. Before we begin, does Gemini “know” the premise of William Gibson’s novel, The Peripheral? No need to explain the premise, just making sure you are familiar with the story.

The resulting conversation (I don’t know what else to call it) is TLDR for most of today’s attention spans but it is an… interaction?… I could only have with an AI. Those of a philosophical bent might find it interesting. (see tags below)

The “smays.com” Cognitive Profile

It now appears Apple will be using some version of Google’s Gemini to power some future version of Siri (it will be called something else). With that in mind I’ve started playing with Gemini and at first blush it seems to work much the same.

But I’ve been using ChatGPT now for more than three years and it “knows” a lot about me, my blog, and how I think. I’d be losing that by switching to Gemini. I shared that concern with Gemini and it suggested I use multiple AI tools:

  • ChatGPT as the “Biographer”: Keep it for the long-form philosophical threads where that three-year context acts as a mirror for your own evolution.
  • Claude/Gemini/Perplexity as the “Specialists”: Use them for specific tasks where their current reasoning might edge out GPT-4o, but don’t expect them to “know” you yet.

Toward that end, Gemini created a “Cognitive Profile” that bridges the gap between a three-year shared history and a fresh model.

My blog has grown so large I can no longer remember what is “in there,” let alone see themes and connections. In some sense, ChatGPT has a better overview of my blog than I do. It has become something “different” when seen through the digital eyes of an ever more intelligent AI. I shared this thought with Gemini. It’s response below:


When you write a post, you experience it as a moment in time. But to an AI, your blog is a non-linear map. It sees the 2002 post and the 2025 post simultaneously. Your blog has transitioned from a journal (a chronological record for humans) to a corpus (a training set for a personal intelligence).

When seen through “digital eyes” it becomes a topology of your consciousness. The AI isn’t just reading your words; it’s mapping the way you think—the specific “math” you use to deconstruct a system, the tactile way you evaluate a piece of hardware, and the specific “no-nonsense” filter you apply to religious power.

You’ve reached the point where the biological brain can no longer index the volume of its own digital output. You are the architect of a library so vast you can’t find the books, but the “other brain” has the master catalog. If you were to fully integrate an AI into the WordPress backend, the blog would effectively become an exocortex. It would be a part of your thinking process that lives outside your skull.

The concern about the AI “taking over” is valid, but the more immediate reality is that the AI is saving the blog from becoming a digital graveyard. Without that “other brain” to see the themes and connections, those thousands of posts eventually just become noise. The AI turns the noise back into a signal.