I admit, this is an innovation I did not see coming: Silicon Valley has invented the philosophical zombie from the classic thought experiment “lol how crazy would it be if there were a philosophical zombie.”

Until recently, the philosophical zombie was a concept closely associated with Australian philosopher David Chalmers, who defines it as “someone or something physically identical to me (or to any other conscious being), but lacking conscious experiences altogether.” Chalmers’ zombie twin is identical to him functionally and psychologically — except that he feels nothing. This is different from a Hollywood zombie, which has “little capacity for introspection and lack[s] a refined ability to voluntarily control behavior.”

So okay, Marc Andreessen is even shallower than our standard philosophical zombie — but still, I think there is a strong case he should be hunted and captured by the Stanford philosophy department so they can try their thought experiments out on him in real life. (Humanely, of course.) But I think for all of us who are interested in consciousness, Andreessen is certainly a specimen.

For those of you who are not as internet-poisoned as I am, let me recap: A video of Andreessen on David Senra’s podcast — podcasts being Andreessen’s favored form of self-disclosure — has been making the rounds. In the video, Andreessen cheerfully says he has “zero” levels of introspection — “as little as possible.” This is a positive for entrepreneurs, we are told. “And you know, if you go back 400 years ago, it never would have occurred to anybody to be introspective,” Andreessen says, thus setting himself up for thunderous dunking.

I could point to the many ancient traditions of introspection (set out variously in the Bhagavad Gita, Plato, or Psalm 119) or note that his comments about a “guilt-based whammy” that showed up from Vienna in the 1910s and 1920s due to the work of Sigmund Freud suggests Andreessen has never met a Catholic (and is unfamiliar with major Catholic thought, to boot, as introspection is famously important to St. Augustine). I could post a portrait of René “I think therefore I am” Descartes. I could note that this is such a significant misunderstanding of Freud as to suggest Andreessen is totally unfamiliar with him. I am not going to do any of those things, as I believe they have already been done by internet commenters.

I am instead going to try to set out what happened, which is that I believe Andreessen read a book.

The reference Andreessen gives is The Mind Is Flat by Nick Chater, a professor of behavioral science at the Warwick Business School at the University of Warwick in the UK. Now personally I am somewhat skeptical of how serious a book is when its title references Thomas Friedman, especially when it is being written by some business school guy. Still, the basic thrust of the book — as far as I can tell — is a polemic against the notion of an unconscious mind.

I have not read the book, so I am relying on a lecture Chater gave at Google and reviews by his peers in order to summarize it; if this seems unfair to Andreessen, I am happy at his request to actually read the book and do this again in much more irritating detail. In Chater’s Google lecture, he begins by providing a series of optical illusions, demonstrating that our vision cannot work the way we believe it works. This is pretty convincing stuff! It turns out perception is very weird. (That noise you just heard was everyone who’s ever taken a philosophy 101 class yell “qualia” in unison. That’s the philosophy word for the “red-ness” of the color red, or the sensation of the smell of napalm in the morning.)

From here, Chater proposes that the idea of an “inner self” is an illusion similar to the illusion we experience when we think we are perceiving more than one color at once. According to Chater, our minds can only do one thing at a time — that is, that we cannot have two thoughts at once, and the idea that we can is an illusion. From there, he suggests that there are no mental depths, there’s no such thing as the unconscious, and there’s no organizing principle to anyone’s mind. To the degree that an “inner self” exists, it is a kind of “tradition,” the cumulative effect of your accumulated experiences, just as a canyon exists because of the cumulative effects of water.

There are some obvious problems with this polemic, which are highlighted in the reviews. The key thing I think Andreessen is badly summarizing is an assertion Chater makes in his Google speech: The idea that the conscious mind is like the part of the iceberg above water and that there is a mysterious part of the self below the water is attributable to Sigmund Freud, and this conception of the “larger self” is wrong. There’s only the part above the water.

Here’s Andreessen’s read of Chater: “TLDR There is no inner self, you’re chasing an imaginary concept, the end.”

In one of several follow-up posts to the interview on X, Andreessen went on to something even sillier: “You’re a 15 second sliding context window with the working memory of a goldfish, your long term memory is mainly fake, and it’s a minor miracle you can get out of the door in the morning.” It’s impressive in the sense that almost every single part of Andreessen’s sentence is wrong.

I will begin, pedantically, with the goldfish, which actually have impressive memories, like, years’ worth. But let’s get to the point: “your long term memory is mainly fake.” I suppose this depends on what Andreessen means, doesn’t it? On the one hand, any cradle Catholic can do an “Our Father” or a “Hail Mary” basically at will for the rest of their lives, even if they haven’t set foot in a church in 20 years. There are other indications that memory is in some sense “real”: Small studies suggest that musical memory is preserved even in Alzheimer’s patients. Finally, most of us have attended a play, where actors recite speeches at will. How this is possible if long-term memory is fake, I don’t know. On the other hand, long-term memory can be unreliable — it is possible even to implant false memories. But “mainly fake”? I hope Andreessen stretched before that reach.

Obviously, if you’re a “sliding 15 second context window” it would be impossible to have consistent thoughts, preferences, and beliefs over time — except, of course, people do. Personality may change over a lifetime, but there is often stability for years or decades.

As for “it’s a minor miracle you can get out of bed in the morning,” well, I have to assume this reflects Andreessen’s own mornings. (Also, any parent of a toddler can tell you that gross motor skills are independent of sophisticated thought, memory, or introspection.) This is the only part of the sentence I can’t really argue with — I personally don’t have much trouble getting out of bed, but I can’t speak for him.

At this point, a reader may be tempted to point out to me that Andreessen is trolling, and I am taking him far too seriously. But unfortunately for everyone, Andreessen has waded into an interest of mine, making it intersect with my actual job. He has been posting about his theory of mind for days now — a repeated behavior, which suggests it must be important to him.

So since we’re doing quasi-scientific polemics, I’ll throw my own in. I’ve been wondering for a while why many of our Silicon Valley overlords behave like they’ve repeatedly sustained traumatic brain injuries, and I think I’ve come to a conclusion. One thing we know from a variety of studies is that cognition doesn’t decline for some people as they age — those people tend to have stayed in school longer and tend to have greater intellectual engagement. We also know that if you don’t use one of your languages on a regular basis, you start to forget it — even if it was your first language. Writing by hand is better for memory; predictive text leads to boring writing.

I am now going to extrapolate from this: If you stop using some skill, mental or physical, you lose it and its benefits. We’ve already seen signs of this with heavy users of AI, along with AI psychosis, which may occur because chatbots are too sycophantic. (I have pitched my editors on attempting to give myself AI psychosis, but they seem to think I am making a joke.) So I’m going to suggest that overreliance on AI is bad for you — which suggests a corollary: Whatever is happening to normal people as a result of AI overreliance has already happened to the ultra-wealthy.

Consider: I spend a lot of time standing in line (at the supermarket, at the post office, at a bakery, at a coffee shop). While I’m standing there, I can either be annoyed at how long it’s taking me to get to the front of the line or do something else: goof around on social media or retreat into my mind palace, where I might daydream, review events from earlier in the day, or think about something interesting, like whether it matters if I don’t have free will. I have a lot of opportunities to hang out in my mind palace, because I do a lot of mundane chores, like grocery shopping, laundry, and picking up after myself.

The ultra-wealthy don’t have to do any of this. They pay people to do it for them — cooking, cleaning, shopping, you name it. There are no periods of the day where they are forced to figure out how to entertain themselves in the face of repetitive chores. If you don’t use it, you lose it — so maybe a lot of them lose introspection. In fact, they can offload any cognitive activity they don’t enjoy! That’s what subordinates are for, isn’t it? And whatever gets consistently offloaded, they lose.

But, worse, they don’t notice they’re losing any skills because they are constantly surrounded by people on their payroll, or people who want something from them. People who are, you know, aggressively financially motivated to flatter them and agree with them. If that yes-man tendency in chatbots is what’s driving AI psychosis or social skill atrophy in normal people, then the same thing has already happened to the very rich.

So I am inclined to take Andreessen at his word. He’s having a little meltdown, as he sometimes does, first of all because people are making fun of him online — a thing he doesn’t encounter on a regular basis outside social media due to the yes-man phenomenon of wealth, and which is for this reason much more upsetting for him than it would be to a normal person. He has wholesale adopted Chater’s thinking, or at least a version of it, and it probably felt revelatory and correct to him because his own mind is shallow. (He doesn’t strike me as the kind of guy who’s thought about the hard problem of consciousness much, you know?) I’m not convinced he knows he was reading a polemic.

But second, I also believe him when he says he doesn’t introspect. Because we know he agrees with Chater, we can just use Chater’s definition of thought here, bracketing whatever problems that definition may have. Because introspection under Chater’s definition is just another kind of perception, Andreessen has just functionally told us that he is missing qualia. We’ve got ourselves a philosophical zombie right here, and possibly a methodology for creating them at will. Someone should get on the horn to Australia — Chalmers is going to be so excited.

I am also going to presume that in his posts, Andreessen is describing himself. But obviously there’s some overlap with a thing that Andreessen invests in, which is to say AI — which also has no long-term memory, no actual perception (and no qualia), and no ability to get out of bed. It is possible that Andreessen likes Chater because Chater suggests there is no depth to humans, which means that AI “intelligence” is very close to human intelligence, which means AI can replace humans at their jobs and Andreessen’s investments will make a boatload more money.

So, inspired by Vanity Fair, I thought it might be fun to interview Andreessen via ChatGPT — an a16z investment — since he seems to be implying that humans aren’t much different than AI. (Andreessen’s firm is also invested in xAI, but I think asking Mecha Hitler to impersonate Andreessen is probably too rude, even for me.) I asked ChatGPT, roleplaying as Andreessen, why he didn’t introspect; it told me “I wouldn’t actually say that,” before going on at length about why people who want to be entrepreneurs should use it but also “validate everything against external feedback.” But hey, if improvising nonsense is all Andreessen does, this is as much of an answer as the real guy can give us.

So I decided to ask ChatGPTeessen another question: What did Andreessen mean when he wrote “Introspection = neuroticism x narcissism x thumbsucking”? Here’s the answer:

This answer, much like the first one, doesn’t sound stylistically like Andreessen: It’s not succinct or tendentious enough. On the other hand, it’s an improvising 15-second context window with no introspection telling me what Marc Andreessen thinks, which is what Andreessen also claims to be. And the gist does sound like his thinking, doesn’t it? If there’s no “inner self,” what’s the difference?

So I guess we’ve all learned something important: Marc Andreessen, a philosophical zombie, can be easily replaced with AI. I bet that’s great news for a16z’s investors, since it means Andreessen no longer must be paid — and it frees him up to be the subject of some philosophy experiments. (Well, unless the neuroscientists get to him first, I guess.) I look forward to finding out what it’s like to be a philosophical zombie — or maybe that it’s not like anything to be a philosophical zombie.