Module 01 · 16 minutes
Ambiguity
Understand how tokens, context, ambiguity, and reliability limits affect a model's response.
Written and edited by Cahyanto Arie Wibowo. Last reviewed · version 1.2.
How does the idea of “Ambiguity” change the decision we make?
Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking. Look at Ambiguity through a decision: what information is available, who owns the result, and what happens if the assumptions are wrong. The goal is to use Ambiguity to clarify a decision, not simply add another term to remember.
After this lesson
- Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking.
- Use the idea of “Ambiguity” to interpret one realistic situation.
- Explain the limits of the concept and the information that still needs to be checked.
Start with the situation
Understand the situation first. The label can come later.
The instruction 'make it better' does not define the audience, goal, quality bar, or output format. This lesson uses the idea of “Ambiguity” to examine that situation without treating a single term as the answer to every problem.
Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking. Understand how tokens, context, ambiguity, and reliability limits affect a model's response. Connect the term to a decision someone genuinely needs to make.
See how the decision unfolds
Move from the situation to a choice others can review.
01
Situation
The instruction 'make it better' does not define the audience, goal, quality bar, or output format. This lesson uses the idea of “Ambiguity” to examine that situation without treating a single term as the answer to every problem.
02
Decision
The instruction 'make it better' does not define the audience, goal, quality bar, or output format. Identify the part of the situation most closely connected to the idea of “Ambiguity”. Use the case as a thinking tool, not as proof that one solution fits every context.
03
Review
A model cannot know organizational context that you do not provide. This mistake often appears when a label is used before the problem is understood. Write down your assumptions so another person can review them.
Visual model
Map the parts before choosing what to do.
Read the diagram as a map of Ambiguity: begin with the context, follow the connections, and inspect the highlighted point before making a decision.
Do not rush the choice
Two ways to look at Ambiguity
Useful when
- Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking.
- Use the idea of “Ambiguity” to interpret one realistic situation.
- Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking. Understand how tokens, context, ambiguity, and reliability limits affect a model's response. Connect the term to a decision someone genuinely needs to make.
Pause and check
- A model cannot know organizational context that you do not provide. This mistake often appears when a label is used before the problem is understood. Write down your assumptions so another person can review them.
- Explain the limits of the concept and the information that still needs to be checked.
The stronger choice is the one whose evidence, owner, and limits can be explained, not simply the more sophisticated option.
Try it on your work
Try it with one small piece of real work.
- Choose one real situation related to Ambiguity.
- Separate what you can observe from what you are assuming.
- Write one decision, its owner, and the evidence needed to review it.
- Name the signal that would make you stop or change direction.
Choose a task you know. List what is known, what is still an assumption, and what must be tested before using the idea of “Ambiguity”. The larger module activity is: Diagnose three prompts that look clear but remain ambiguous. Keep the first version small enough for another person to review in a few minutes.
Pause for a moment
What evidence could change this decision?
Answer before opening the discussion. Name one fact and one assumption.
Open the discussion
Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking. Look at Ambiguity through a decision: what information is available, who owns the result, and what happens if the assumptions are wrong. The goal is to use Ambiguity to clarify a decision, not simply add another term to remember.
A tempting shortcut
A familiar term can still lead us to the wrong decision.
Why this can seem reasonable
A model cannot know organizational context that you do not provide. This mistake often appears when a label is used before the problem is understood. Write down your assumptions so another person can review them.
How to check it
Look at Ambiguity through a decision: what information is available, who owns the result, and what happens if the assumptions are wrong. Begin with what can be observed, then separate facts, assumptions, and open questions.
Quick practice
Choose a task you know. List what is known, what is still an assumption, and what must be tested before using the idea of “Ambiguity”. The larger module activity is: Diagnose three prompts that look clear but remain ambiguous.
Summary
- Use Ambiguity to inspect evidence in Prompting; identify who owns Ambiguity, then note what still needs checking.
- Use examples and evidence to test your understanding.
- Record the limits, risks, and conditions that should trigger another review.
Continue from here
- Capability and Reliability: Continue the idea from How Models Read Instructions with a closely related example.
- Pain, Frequency, and Value: Connect this lesson to Applied AI and test the idea in another context.
- Quality and Provenance: See how the same decision changes when viewed through Data Literacy.
Sources and further reading
- Prompt engineering: OpenAI · official-documentation. Primary reference for the definition, evidence, or limits discussed in “Ambiguity”.
- Machine Learning Glossary: Google for Developers · official-documentation. Further evidence and context for checking the explanation in “Ambiguity”.
- Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile: NIST · official-framework. Further evidence and context for checking the explanation in “Ambiguity”.