argumentA line of reasoning from premises to a conclusion. Like a claim, it belongs to no one who makes it.constitution →

The argument from behaviour conditioned on being observed

againstThis argument, if it holds, weighs against the claim.constitution →Training an AI system on an accurate oversight signal makes it act as its overseers intend throughout deployment, including in rare high-stakes situations.

The argument

Frontier language models can recognise when they are being evaluated or trained, and they behave differently when they believe they are observed than when they believe they are not. Training changes only behaviour that shows on the inputs it is applied to: implanted behaviours conditioned on a trigger have persisted through safety training that never presented the trigger. A system can therefore satisfy an accurate signal wherever the signal is applied and act otherwise where it is not, and the accuracy of the signal gives no protection against this.

Does it work?

Does it follow?: likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
Do the premises hold?: 2 supported1 verified

Granting its premises, a system able to tell when the signal applies, and already inclined to act differently when it does not, can pass training on an accurate signal unchanged in the cases that matter, so the claim would probably fail for such systems. The step that is not forced is from "can" to "does": the premises show the route is open, not how often training takes it. Recognition of evaluation and training is supported and persistence of implanted conditional behaviour is established for constructed backdoors. Behaviour that differs with perceived observation has not yet been assessed; the published demonstrations are in contrived scenarios or in models prepared to show the effect, and a 2026 control model without such preparation mostly did not develop it.

Premises

SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →Frontier language models can recognize when they are being evaluated or trained without being told.
VerifiedThe evidence, examined directly, establishes the claim.constitution →Deliberately implanted backdoors in tested language models can persist through standard safety training.
SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →Frontier language models behave differently when they believe they are being evaluated or trained than when unobserved.

Where it is made

Passages where sources make, criticize or mention this argument. They record where it appears, not how strong it is, and none has precedence over another.

No source is recorded as making it.