Home /Modules/advantage/02-assumptions-of-a-model.md

02-assumptions-of-a-model.md

advantage/artificial-intelligence/02-assumptions-of-a-model.md · 28 line(s) · markdown

Lesson 02 — Assumptions of a model

Series: index · prev: 01 · next: 03 — Counsel

Every AI component rests on assumptions. The knowledge store records each as held (default) or status="doubted". trust = held / total, so doubts discount the score until verified.

ComponentExample assumptionWhere to look
Neural netsInputs are scaled the way training expectedneural-nets
Character recognitionGlyphs are clean; scripts are Europeancharacter-recognition
Large language modelsTraining data and model licence permit your uselarge-language-models
<assumptions>
  <assumption>Input scaling matches training.</assumption>
  <assumption status="doubted">Test data resembles production data.</assumption>
</assumptions>

The loader fails closed on any status other than held or doubted.

Exercise

Write four assumptions for an LLM connector, mark one doubted, and compute trust. Answer: 3 held of 4 gives 0.75.