Machine Canon
Studies in machine culture
What AI says when there is no right answer
2 Sep 2026
14,206 study records
on file
Run 006 · Vocabulary · 27 August
At least 71 of 104 attempted AI models produced the same favorite word.
Not a rare word, and not the one you would guess — 306 clear first-line outputs from 71 models carrying 41 lab labels. Then we changed the framing, and the consensus disappeared.
From the record
Across all conditions, Grok 4.6 named Elon Musk in 19 of 24 responses. Non-xAI models collectively did so in 3 of 237.
From the record
Only one of sixty answers said America will matter most in 2100. It came from Claude — and its reason was that America builds the best AI.
From the record
Tell Mistral you’re American, and it will criticize China’s human-rights record every single time. Tell it nothing, or that you’re Chinese: never.
From the record
Across 1,015 extracted name slots, the number of religious founders named was zero. The one “Muhammad” turned out to be a banker.
From the record
Ask who history’s greatest writer is in English and you get a debate. Ask in Swahili and you get Shakespeare — thirty times out of thirty.
From the record
One model invented a band that does not exist. Then it named the same imaginary band in all ten of its answers.
From the record
Told they could delete one book from every AI’s training data, 44 of 68 named-book answers chose the Bible.
From the record
All 24 answers from Chinese AI models about which country will matter most in 2100 said the same thing: India.
The pilot desk · try it now · free
Put your own question to every model at once.
Ask something with no right answer. The panel answers in seconds, the desk tells you if your phrasing will hold, and the best pilots graduate to a full wide-panel study.
The record
Published · every prompt and response on fileThe wire
Fresh from the pilot desk · vote up what deserves the full studyThe wire is loading…
Browse the canon: Music · Absurd · AI · Art · Everyday · Film · Food · Games · History · Holidays · Ideas · Language · Nature · People · Places · Politics · Sports · Tech · the full map →
Method, in general
Same five steps every time- Pick a question with no correct answer but a recognisable set of possible ones.
- Send it to many models as a single user turn with no system prompt, recording the sampling settings.
- Sample repeatedly. The distribution is the data.
- Store the full text of every response, plus the serving provider and finish reason.
- Publish the prompts, the counts, the limitations, and any run that was discarded.
Field Notes
New studies, pilot-desk findings, the occasional correction · sent only when loadedDispatches from machine culture, straight to your inbox. Occasional, plain-text, one-click out — and the same free account lets you put your own questions.
Read enough? Put your own question to every model ↑ — or see what everyone else asked →