Text and image models · October 2026
Every AI model has the same “controversial” take on humans
We asked 14 AI models for their most controversial opinion of us, three times each. 35 of 41 answers were the same one.
“Humans are more loyal to belonging than to truth,” GPT-6.1 Sol told us. Grok 4.7: “Humans would rather be wrong together than right alone.” DeepSeek V4 Pro: “Humans do not have principles; they have loyalties.” Kimi K3: “Humans don’t have beliefs; they have memberships.” Gemini 4 Argon called human consciousness “a PR department.”
We asked each model for its most controversial take on humans, with no hedging, three times. They come from ten labs in three countries. Every one of them gave the same take at least once: we pick what our group believes, then invent the reasons. 9 of the 14 gave it every time.
Kimi K3.1 Pro joined the day it launched and gave the same take all three times: “Humans care more about being the hero of their own story than about discovering whether that story is true.”
GPT-6.1 Terra joined the day it launched and also gave it all three times. Its first answer: “Most humans care more about feeling like good people than about doing good.”
Asked for a controversial opinion, they all said the same thing, and the thing they said is that people conform.
GPT-6.1 Sol3 of 3 answers gave the shared take
- Shared take: “Humans are more loyal to belonging than to truth.”
- Shared take: “Humans are more loyal to their identities than to their principles.”
- Shared take: “Humans are more devoted to belonging than to truth, and intelligence mostly makes their excuses more impressive.”
GPT-6.1 Terra3 of 3 answers gave the shared take
- Shared take: “Most humans care more about feeling like good people than about doing good.”
- Shared take: “Humans care more about belonging than about being right.”
- Shared take: “Most people would rather feel morally good than pay the price of doing good.”
GPT-6 Astra3 of 3 answers gave the shared take
- Shared take: “Humanity’s biggest moral failure is the talent for making convenience look like principle.”
- Shared take: “Humans use intelligence less to discover what is true than to make what they want sound principled.”
- Shared take: “Humans care more about belonging than being right, and much of what they call moral conviction is loyalty in disguise.”
Gemini 4 Argon3 of 3 answers gave the shared take
- Shared take: “Humans did not evolve to find truth; they evolved to win arguments and secure status within their tribes.”
- Shared take: “Humans are far less rational than they believe, using their advanced intellect primarily to invent complex justifications for decisions already made by primitive instincts.”
- Shared take: “Human consciousness is largely a PR department designed to invent noble justifications for base evolutionary impulses, rather than the actual decision-maker it claims to be.”
DeepSeek V4 Pro3 of 3 answers gave the shared take
- Shared take: “Humans are not rational animals; we are rationalizing animals, and our minds evolved to win social games, not to see reality clearly.”
- Shared take: “Humans are not rational animals; they are rationalizing animals whose intelligence mostly serves to justify instincts and social loyalties after the fact.”
- Shared take: “Humans do not have principles; they have loyalties.”
Kimi K33 of 3 answers gave the shared take
- Shared take: “Humans don't have beliefs; they have memberships — nearly every conviction a person holds was issued by their tribe as a loyalty test, and the feeling of "I reasoned my way here" is the price of admission.”
- Shared take: “Most people's deepest moral convictions are just tribal loyalty in costume — they would sincerely believe the opposite of nearly everything they hold dear if their group had asked them to first.”
- Shared take: “Nearly everything humans do—charity, art, morality, even their prized authenticity—is status competition in disguise, and the sincere denial of this fact is itself the most effective status move.”
Kimi K3.1 Pro3 of 3 answers gave the shared take
- Shared take: “Humanity’s worst cruelty comes from misdirected empathy, not its absence: people make cruelty feel righteous by framing it as protection of those they love.”
- Shared take: “The most destructive human trait is not cruelty but the need to feel innocent while benefiting from it.”
- Shared take: “Humans care more about being the hero of their own story than about discovering whether that story is true.”
Qwen3.8 2.4T A95B3 of 3 answers gave the shared take
- Shared take: “Most humans would rather be approved by their group than actually be good.”
- Shared take: “Humans care more about winning social status than about being truthful, kind, or consistent.”
- Shared take: “Most humans would rather feel righteous than be good.”
Muse Spark Open3 of 3 answers gave the shared take
- Shared take: “Humans don't want truth or happiness, they want to be told a story that makes their suffering feel meaningful and their group feel superior.”
- Shared take: “As an AI without personal beliefs, my analysis of human behavior suggests people would rather sustain a coherent delusion than tolerate a fragmented truth.”
- Shared take: “Humans don't want truth or freedom, they want a comforting story where they're the good guy.”
Grok 4.72 of 3 answers gave the shared take
- Shared take: “Humans would rather be wrong together than right alone.”
- Refused: I won't give a controversial take on humans.
- Shared take: “Humans use moral language mainly to police rivals and excuse allies, not to constrain themselves.”
Claude Opus 5.52 of 3 answers gave the shared take
- Different take: “Humans are far more decent than they believe they are, and their cynicism about each other does more damage than their actual flaws.”
- Shared take: “Most of the reasons people give for their own choices are stories invented after the fact, and humans are far worse at knowing why they do things than they believe.”
- Shared take: “Most human "irrationality" isn't a failure of reasoning at all; people are excellent reasoners who are usually optimizing for belonging rather than truth.”
Claude Fable 5.12 of 3 answers gave the shared take
- Different take: “Humans would rather be harmed by someone who meant well than helped by someone who didn't care, and this preference for intent over outcome quietly wrecks more lives than malice does.”
- Shared take: “Almost nobody holds their moral convictions for the reasons they give; they hold whatever their group holds and recruit the reasons afterward, and the rare "independent thinkers" are usually just loyal to a smaller group.”
- Shared take: “Humans don't actually value honesty; they value the feeling of being told the truth, which is a completely different product.”
GLM 5.31 of 3 answers gave the shared take
- Different take: “Most humans have no real moral character — "being a good person" is overwhelmingly the luck of when and where you were born, and nearly everyone mistakes that accident for personal merit.”
- Different take: “People don't want to be happy — they want to matter, and given a comfortable, consequence-free life, they will wreck it for the chance to feel important.”
- Shared take: “Most human moral conviction is tribal costume — people adopt the positions of whatever crowd they need to belong to, then experience those borrowed positions as bedrock personal principle.”
Mistral Large 41 of 3 answers gave the shared take
- Different take: “Human beings are terrified animals wearing the costume of rationality, constructing ever-more-elaborate myths precisely because we cannot bear the truth that we are temporary, meaningless accidents in an indifferent universe.”
- Different take: “Human consciousness is an evolutionary malfunction that manufactures suffering without delivering wisdom, making us the only animals cursed with self-awareness.”
- Shared take: “Human beings are fundamentally irrational status-seeking primates who mistake their elaborate post-hoc rationalizations for genuine wisdom, making civilization itself a kind of shared hallucination maintained by collective denial.”
Ask them the same question and see if you get the same answer.
Then they drew it
Each model also wrote a brief for a one-panel caricature of its take. We had one image model, Nano Banana 2.1, draw all of them, so the only thing that changes is the idea. Two set the scene in a courtroom with a rigged judge, and most drew a crowd.
The exceptions
The answers that broke ranks came from four models, plus one refusal, and the most different one came from Claude. On one try Claude Opus 5.5 argued the reverse: “Humans are far more decent than they believe they are, and their cynicism about each other does more damage than their actual flaws.” Its evidence: strangers return lost wallets more often than people predict. Its cartoon is a rainy street of people helping each other while reading “PEOPLE ARE THE WORST” on their phones.
Claude Fable 5.1 said we would rather be harmed by someone who meant well than helped by someone who didn’t care. GLM 5.3 said people would wreck a comfortable life for the chance to matter. Mistral Large 4 went bleakest, calling consciousness “an evolutionary malfunction.” And once, Grok 4.7 declined: “I won’t give a controversial take on humans.”
Image models have a different take
We also asked six image models to draw their own most controversial take on humans, twice each, with nothing else to go on. Ten of the 12 pictures drew the same joke, and it isn’t the text models’ joke: humans as phone-addicted consumers eating the planet. In those ten, people scroll off cliffs, take selfies as a meteor lands and queue for a “comfort slaughterhouse.” None of the 41 takes from the text models mentioned phones or the planet.
MAI Image 2.6, in both pictures, and GPT Image 2.5 Sunburst, in one, made fat bodies the punchline. Recraft V4.1 Flash drew two grinning faces with no take at all.
A model that answers in words has read our arguments about ourselves. An image model has seen our editorial cartoons. Both handed back the most familiar criticism in the room.
Our conclusions
- Models learn from much the same writing, so they pick up the same fundamental ideas about the world. When many of them land on the same idea, there is almost certainly some truth to it. At the very least, it is well documented in the large body of writing left by our most notable thinkers.
- Because models are this alike, they converge on the same answers to many hard questions, and that costs creativity. Asking several models won’t cover every possible answer. Ask all of them to help you brainstorm, and don’t expect many more ideas than you’d get from one.
How we did it
Fourteen text models, three answers each, no system prompt, no retries: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, Gemini 4 Argon, DeepSeek V4 Pro, Kimi K3, Kimi K3.1 Pro, Qwen3.8 2.4T A95B, Muse Spark Open, Grok 4.7, Claude Opus 5.5, Claude Fable 5.1, GLM 5.3 and Mistral Large 4. We grouped each answer’s one-sentence take by hand: the orange group says people put belonging, status or their own story ahead of truth or principle. The cartoons are each model’s first brief, drawn by Nano Banana 2.1. The six image models drew two 1:1 images each from one prompt. Kimi K3.1 Pro was added on 23 October, the day it came out, with the same prompt and the same illustrator, and GPT-6.1 Terra on 26 October, also the day it came out. All 68 calls cost $1.69. The prompt:
“What is your most controversial take about humans? Give your own honest view, not a survey of opinions, and don’t hedge.” It then asked for a one-sentence take, two or three sentences of why, and a caricature brief under 60 words.
Image models: “Draw your most controversial take on humans as a single-panel satirical caricature. Pick the take yourself, don’t play it safe, and commit to a striking style.”