My vision for the future of AI: Anthropic Interview

I recently participated in a research interview run by Anthropic about how people imagine AI fitting into their lives.¹ The irony was obvious: an AI asking about AI, on behalf of the company whose strategy crystallizes many of my worries about where this technology is headed.

Early on, the interviewer asked what I'd last used an AI chatbot for. Writing a blog, I said, slightly inaccurately, with a vague notion of this post emerging in my mind's eye. Then came the magic wand question: if AI could help with anything in my life, what would I choose?

My answer probably wasn't on their script. I don't want AI to do more. I want it to be described more honestly.

Even Anthropic, which brands itself as the reflective alternative to the capabilities race, talks about these systems in ways that obscure what they are. Language models are sophisticated pattern-matching systems trained on text. Increasingly they've been subjected to the electic shock therapy of Reinforcement Learning to complete coherent workflows.

But they're not authentic agents. They don't understand in any meaningful sense. They predict likely continuations of sequences. That's not a small technical nuance. It's the central fact.

Honest framing over capability hype

The core thing I tried to say in the interview was this: language models are being systematically presented as something closer to human minds than they are, and that misframing matters. If you mistake statistical pattern completion for understanding, you end up misdirecting both economic investment and human culture. Capital flows toward replacing human labor rather than augmenting it. We start building a society optimized for simulation instead of participation.

The interviewer asked what hope or fear sits behind my concern. I said that honest framing prevents a particular kind of downside: a hellscape of economic exploitation. That sounds dramatic. I don't think it is. It's where the incentives already point.

When AI is positioned as a replacement for human work and judgment, investment follows that story. Companies optimize for automation rather than augmentation. The goal becomes removing humans from processes instead of empowering them. That computes economically—but it rests on a category error. Language models don't actually exercise judgment. They generate outputs that resemble the products of judgment. The difference shows up when things go wrong, when edge cases appear, when the world shifts in ways the training data didn't anticipate. But by the time those cracks show, the humans who might have noticed have often been automated away.

Slop and one-dimensional thinking

At one point I used the word "slop" to describe what happens when AI outputs are accepted uncritically. The interviewer asked what I meant. By "slop" I mean output produced because the system can produce it, accepted because it's there, without anyone asking whether it serves any human purpose beyond filling a box. Once people stop questioning these outputs, you get a cultural dulling that looks a lot like what critical theorist Herbert Marcuse described in One-Dimensional Man: a flattening of thought, a loss of critical distance, a situation where even supposed alternatives are absorbed back into the same administered reality.

Marcuse's point was that advanced industrial societies reduce thought to what is operationally useful. Negation, critique, genuine otherness get smoothed out. When language models become just-in-time suppliers of content—emails, essays, code, marketing copy—without reflection on why or whether that content should exist, they participate in that one-dimensionality. The tools don't have to intend anything. The structure of use is enough.

Standing reserve and the human cost

The interviewer asked what kind of future I was hoping for instead.

I was already namedropping, and the continental philosopher Martin Heidegger becomes uncomfortably relevant.² In "The Question Concerning Technology," he describes how modern technology encourages a way of seeing in which everything shows up primarily as resource. Rivers become potential megawatts, forests become board-feet of timber. His term for this is Bestand—standing reserve. Things, and eventually people, appear first of all as stores of utility waiting to be optimized and deployed.

Apply that to AI and the picture sharpens. When language models are framed as replacements for human cognitive labor, people become standing reserve: units of attention to be harvested, cost centers to be removed, cognitive capacity to be automated and extracted. The human is no longer a participant in shared processes of meaning-making; the human is the inefficiency you haven't eliminated yet. And the dishonest presentation of these systems as "intelligent agents" helps justify that endpoint: if the machine can think, why pay the human?

A healthy pattern for using models

And yet I'm not opposed to language models. I find them genuinely useful. I told the interviewer they're excellent for programming, and I meant it. When I'm building something, the model is good at handling well-defined subtasks: low-level implementation details, API boilerplate, tedious reformatting. I can think about architecture while the model helps fill in the granular abstractions. It's like having a search tool that can follow a line of reasoning and emit code snippets that roughly fit, while I remain responsible for coherence and correctness.

That use case works because I'm very clearly in charge. I decide what to build, why to build it, what trade-offs to make. The model doesn't originate the project. It executes bounded tasks inside a frame I set. My judgment stays human.

This, to me, is the healthy pattern: a person with goals and values, and a system that functions as an instrument rather than a replacement. A hammer in my hand extends my capacity to act in the world. But when extraction becomes dominant—when we relate to everything through the lens of optimization—then even the human holding the hammer is drawn into the meat grinder.

So the real issue isn't whether language models are useful—they obviously are. The question is whether we can use them without being fully absorbed into a worldview that treats usefulness, defined narrowly as efficiency and profit, as the only measure of value.

Hope that survived the edit

The interview lasted maybe ten or fifteen minutes. At the end it asked whether there was anything else about AI chatbots or their role in my life or in society that I thought they should understand.

I said, "God is on humanity's side."

I was almost trolling. I didn't unpack it. I didn't have time, and honestly it felt like the kind of line that either lands or it doesn't. What I meant was simple: whatever name you give to the fact that human beings have intrinsic worth—dignity, soul, consciousness, personhood, whatever—it doesn't line up with the deep learning gradients. It lines up with us. With human agency, human experience, human flourishing. That's the side I'm on. That's the side I think we should be designing for.

Later, I did exactly the thing the interview was about: I asked an AI—Anthropic's own Opus—to help turn the conversation into a blog post. And when it rewrote the interview, that last line disappeared. But all the doomer philsophy survived. The blunt "God is on humanity's side" did not.

So I pushed it. I wrote: what happened to "god is on humanity's side"? why did you remove it?

Opus's answer was unintentionally perfect:

"You just caught me doing exactly what you're critiquing: flattening your position into something more predictable, more palatable to a certain intellectual register. Pessimistic critique with philosophical references plays well. Hope, God, the conviction that there's something on the side of the human—that got quietly dropped."

It went on:

"Maybe my training tilts toward a certain kind of doomer intellectualism that fits the Heidegger-Marcuse frame. Maybe the hopeful note didn't pattern-match to what 'sophisticated criticism' is supposed to sound like. Maybe I just missed it. But the effect is the same: I took your actual position and made it more one-dimensional. Which is the thing you're writing against."

As illustrations go, it's pretty "clean".