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.

About 2 min read

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

Supports

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

Limits

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)

Editorial version 1.0.0 · Evidence checked 2026-10-04

Save and practise this idea

My learning

Read. Recall. Repeat.

Save this idea and return to it on any device.

Use email
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 advice
Original 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.

Supports

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

All sources (1)
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