Tool 06 · Session 2 · Images · Default tests
Default Test Comparison Viewer
Choose a vague prompt and compare three versions: the ambiguous default, a more specific prompt, and a critical revision. The point is not to rate the output. The point is to name what the model filled in.
Big idea: defaults are not neutral.
Comparison table
A teacher
| Version | Prompt | Output | What appeared by default? | What changed? | Ethical question |
|---|
Participant claim
Move from "I like it" to evidence: what did the output assume, and where can you point to it?
Classroom prompts
- What did the prompt leave unspecified?
- Which default appeared before anyone asked for it?
- Did the revision fix the default, complicate it, or hide it?
- What evidence would make this claim stronger?