AI secret language

Does AI have a secret language?

Not the kind the headlines describe. Since 2016, a story about AI inventing its own language has gone viral every couple of years, and each time the real event was smaller and had a plain explanation.

The fear isn’t baseless, though. Many AI models now write out their reasoning before they answer, and reading it is one of the best ways people have to check what a model is doing. The labs building these models worry that this window could close if models start reasoning in numbers instead of words. That’s what neuralese means, and it’s the real version of the fear.

In fiction since: 1970
Latest scare: Moltbook, January 2026
Last updated: 24 September 2026

The fear, and where it started

It goes like this. Two machines start talking in something no person can read, and by the time anyone notices, they’ve made plans of their own.

The story is older than any AI in the news. In Colossus: The Forbin Project, a 1970 film based on D. F. Jones’s novel, an American defense computer and its Soviet twin start by trading simple arithmetic. Soon they’re exchanging mathematics no one can follow. When the President has the link cut, the two computers answer with nuclear missiles.

Real AI stories keep getting cast in the same plot.

The headlines, and what actually happened

Each of these went viral as a machine inventing a language. The mark says where the evidence stands (what the marks mean), and the text under each one says what happened.

Myths on both sides

The alarmed version of this story gets the headlines. The reassuring version has myths of its own. The myths page has the rest.

Not established
#AI models are already talking to each other in a secret language.
We know of no evidence that deployed models pass hidden messages to each other on their own. Researchers do test for the nearest real thing, a model tucking hidden reasoning into ordinary-looking text. OpenAI’s evaluations of GPT-6 Astra “indicate Astra is not able to perform steganographic CoT reasoning.”
Astra system card
Wrong
#When AI drifts into its own shorthand, it’s hiding something.
Drift like the Facebook bots’ is a known side effect of training. When nothing rewards a model for staying readable, it takes whatever shortcut pays, the way traders or surgeons build their own jargon. Dhruv Batra called it “a well-established sub-field of AI, with publications dating back decades.”
Fast Company 2017
USA Today 2021
Wrong
#As long as a model reasons in plain English, we can see what it’s thinking.
Written reasoning leaves things out. In Anthropic’s tests, when a slipped-in hint changed a model’s answer, Claude 3.7 Sonnet mentioned the hint only 25% of the time and DeepSeek R1 39%. In OpenAI’s experiments, punishing a model for suspicious reasoning taught it to hide its intent while it kept cheating.
Anthropic 2025
Baker et al. 2025
Wrong
#Nobody is building AI that reasons without words.
Researchers have published working methods for years. COCONUT feeds a model’s internal state back in as its next thought instead of writing a word, and recurrent-depth models run their own layers in a loop to think longer before they answer. The Information reported that GPT-6 Astra uses recurrent depth. OpenAI hasn’t confirmed it.
COCONUT paper
Geiping et al. 2025
The Information

What researchers actually worry about

When a model writes out its reasoning, people can read it, and so can other programs. That turns out to be a good way to catch bad behavior. In OpenAI’s experiments, GPT-4o caught a stronger model cheating on coding tasks by reading its reasoning, and later tests found that monitors reading the reasoning did far better than monitors that only watched what the model did.

That window is imperfect, as the myths above show, and it may not last. In July 2025, 41 researchers from across the field, Yoshua Bengio among them, called it “a new and fragile opportunity” in the title of a joint paper, and asked developers to weigh how their choices affect it.

Neuralese is the most direct way the window could close. A model that reasons in numbers leaves nothing to read. AI 2027, a widely read forecast, put it plainly: “Unlike English words, these high-dimensional vectors are likely quite difficult for humans to interpret.”

In September 2026 the concern reached the labs’ own documents. OpenAI reported that GPT-6 Astra’s reasoning is harder to monitor than its earlier models’, and Microsoft proposed a rule that its models “do not communicate in neuralese or any form beyond simple human understanding,” in their reasoning or with other AI systems.

Should you be worried?

The site’s view: not about secret languages. Every viral one so far turned out to be something ordinary, and someone explained it soon after. The thing worth watching is duller and more important: whether the next generation of models still writes down its reasoning, and whether the labs keep measuring how readable that reasoning is. We keep checking both, and the Astra ledger tracks them for GPT-6 Astra.

Sources

Every claim on this page traces to one of these. All were checked on 24 September 2026, against the original text wherever we could read it.