PWR-173 · Empathy, Social Cognition & Trust

Trust calibration

Trust can be calibrated to a specific tool and task—but no prompt teaches a universal instinct for people or AI.

Read the complete explanationCompare the Frontier record

Revision 7T · Full Tutorial Edition · Release manifest · Methodology · Corrections

One source of teaching truth

Canonical Power learning unit · TLU-PWR-173

The learner records an independent answer, observes advice quality by stratum, accepts or rejects advice for stated reasons, and reports over-reliance and under-reliance separately.

Canonical Power page
PWR-173 · Trust calibration
Full tutorial
Open full tutorial
Practical authority
The tutorial teaches a low-risk method that may be practised inside its stated limits.
Current treatment
Full low-stakes tutorial
Research depth
focused · 3 bound sources
Risk framing
moderate to high
Capability self-practice
Permitted inside the tutorial's stated low-risk limits
Pathway membership
Retained external route · SP-HUB-RESEARCH

Open My Power Path Inspect the canonical record

Read before using this page

Explanation is not permission.

This dossier explains the evidence and its limits. It is not a diagnosis, personal recommendation, assessment, clearance, performance promise or training programme. Actionable teaching appears only when the canonical Power record explicitly authorises it.

Complete bounded explanation

What this power means.

Capability to develop or express trust calibration in a declared context without inheriting broader claims.

What the current evidence supports

Human–AI reliance can be better calibrated in some configured interfaces, but feedback effects conflict and do not transfer automatically.

How to observe or measure it without overclaiming

Declare trustee or system, version, task, reliability distribution, appropriate-reliance rule, over- and under-reliance, outcome and delay; expressed trust is not calibrated trust.

Myth

Install a perfect trust detector

Metric

Appropriate reliance, over-reliance and under-reliance across known reliability conditions

Boundary

Calibration to one system cannot rank people or transfer to every model, relationship or institution.

Negative and limiting findings

  • Explicit trust-calibration feedback was null on key outcomes.
  • No device-off retention or cross-domain transfer was shown.

Claims this evidence cannot support

  • know who to trust instantly
  • perfect trust instincts
  • AI trust score
  • eliminate manipulation
  • rank trustworthy people

Individual tutorial · FULL SELF GUIDED TUTORIAL

How to learn this Power now.

The learner records an independent answer, observes advice quality by stratum, accepts or rejects advice for stated reasons, and reports over-reliance and under-reliance separately.

  1. Get readyUse a fictional adviser and harmless answer-key task.
  2. Learn the method8 concrete steps teach the permitted method from start to finish.
  3. See right and wrong4 comparisons show correct or safer execution beside common wrong or riskier choices.
  4. PractiseRun one 24-item calibrated deck, then a 12-item delayed deck after 48 hours. Repeat monthly with a changed reliability distribution; rewrite the rule whenever version or condition changes rather than carrying old trust forward.
  5. Check progressBaseline fixture: A fictional weather adviser answers 24 map questions: it is correct on 6 of 8 clear-map items, 4 of 8 blurry-map items and 2 of 8 reversed-key items. An answer key permits exact scoring. Enter success checks from “Define appropriate reliance” and “Score four outcomes”. If “Let the adviser’s wording become the starting answer.” occurs, apply its named fix; then score Appropriate reliance, over-reliance and under-reliance across known reliability conditions on the unused “Test without feedback” item.

Authority boundary: Titan teaches a concrete low-stakes method step by step while keeping evidence and transfer claims bounded. The method is Power-specific; its actionability follows this treatment.

Open the full tutorialOpen My Power Path

Related Powers: PWR-169 · PWR-170 · PWR-171 · PWR-172

Direct evidence register

Sources that support—and limit—the claim.

Citation roles are explicit. A source may support existence or trainability while simultaneously limiting transfer, certainty, generalisation or safety.

  1. Primary empirical supportLimiting / contrary
    Calibrating Reliance on Automated Advice: Transparency and Trust Calibration Feedback

    Monica Tatasciore; Shayne Loft · 2025 · Primary research

  2. Primary empirical supportLimiting / contrary
    Adaptive trust calibration for human-AI collaboration

    Kazuo Okamura; Seiji Yamada · 2020 · Primary research

  3. Limiting / contraryOfficial boundary context
    Employment practices and data protection: monitoring workers

    Information Commissioner’s Office · 2023 · Official authority

Current teaching and evidence boundary

The next gate remains visible.

External confirmation is required before higher-authority use because: a clinical, high-risk or regulated configuration.

A Power-specific tutorial is available at /tutorials/pwr-173/. It contains a plain-English method, 8 ordered steps, a worked example, right-versus-wrong comparisons, specific mistakes and corrections, practice, measurement, accessibility, stopping rules and evidence. Its self guided mode remains controlling.