Principle
Polished wording is not a confidence test
Before trusting an answer that sounds certain, ask what you checked beyond its presentation and your expectations of AI.
Before you use it
- Use when
- A model's answer feels certain because it is fast, polished or direct.
Keep this limit in mind
- Clear communication is useful; this rule separates readability from epistemic confidence, not from quality.
Current editorial reading
Distinguish an impression from a signal
Perceived confidence is your impression of how sure an agent seems. It is different from an uncertainty measure that has been tested against correct and incorrect answers. In experiments with matched human and artificial-agent behavior, prior beliefs about capability affected attributed confidence. The work did not test whether fluent prose caused that effect, and the pattern varied with the task.
Check the claim that matters
Use the stakes to choose a source check, calculation or independent review. For example, a polished answer gives a product retirement date while a colleague sounds unsure. Open the vendor notice and check the exact product version; tone does not settle the date. If a confidence score is available, ask how it was tested on this kind of question before using it to change your review.
Take it with you
You should be able to name the evidence behind your reliance without saying that the answer sounded confident. Readability remains useful; it is not a substitute for that evidence.
Sources and evidence (1)
What we checked
Matched observable behavior received different confidence attributions depending on agent identity and prior beliefs about capability.
This concerns attributed confidence, not a measurement of a model knowing whether it is correct.
Beliefs about accuracy shape confidence attributions to humans and artificial agents · Publisher-indexed Methods; Experiment 7; Discussion
The experiments concern observed choices and response times; they do not isolate linguistic fluency as a cause.
The emotion-categorization task also bounded the effect. The reader-facing source check is a practical inference, not an experimentally validated intervention.
Beliefs about accuracy shape confidence attributions to humans and artificial agents · Publisher-indexed Methods, Experiments 1–7; Experiment 6 and Discussion
Editorial sources (1)
Save and practise this idea
My learning
Read. Recall. Repeat.
Save this idea and return to it on any device.
Keep exploring
Connected ideas
You are readingPolished wording is not a confidence test
More from this collection
Calibrate when to rely on AI instead of measuring trust as a feeling
Test actual skill before letting perceived expertise override AI adviceOriginal edition evidence and sources
These records belong to the original released edition. The current editorial reading has its own evidence above; neither set silently replaces the other.
Seven preregistered experiments found observers systematically attributed greater confidence to AI agents than humans even when observed behavior was identical.
Confidence attribution is not the same as actual model confidence.
Beliefs about accuracy shape confidence attributions to humans and artificial agents · Abstract
Original edition, downloads and provenance
The reading above is editorial version 1.0.0, bound to this exact source edition. The original data and saved downloads retain that edition and the separate editorial layer. They may contain earlier wording; use the current reading above when interpreting it.
Version 0.1.0
No review details are supplied for this edition.
Read the original edition and overlay as JSON · Release details