Source and example scope
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
Provide the remark and the event it describes. Compare ironic praise of a negative event with literal praise or criticism, preserving ambiguous intent rather than claiming to know the speaker's thoughts.
The word wonderful does not settle the label. The first example supplies a failed operation alongside apparent praise, so the contradiction becomes evidence for an ironic reading. The successful export supplies the opposite context.
Literal criticism is a separate outcome. Calling a failure frustrating does not require an ironic interpretation. The ambiguous example preserves uncertainty rather than attributing an intention that the text never establishes.
The source post reports difficulty with sarcasm classification. These authored cases make that limitation testable; they do not claim to reproduce its dataset or improve its accuracy.
These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Use the sample to understand the rule, then test your own input for sarcasm context check.

Provide the remark and the event it describes.

Open the decision rules and keep the intended distinction between Sarcasm cue, Literal praise, Literal criticism, Ambiguous, Need evidence. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review Ambiguous, Need evidence before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Crash called wonderful | Sarcasm cue | 100% |
| Fast export | Literal praise | 100% |
| Direct complaint | Literal criticism | 100% |
| No stated intent | Ambiguous | 76.0% |
| Quoted praise used ironically | Sarcasm cue | 100% |
| Missing remark | Need evidence | 100% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.jsonThe rubric explains the decision; the application owns the next step.
No. A direct negative complaint belongs under Literal criticism. Sarcasm cue requires apparent praise that conflicts with a supplied negative event.
Yes. Great, another update may be sincere after a useful release or ironic after a repeated disruption. Keep the event in the input and preserve ambiguous wording.
No. It is the model distribution for this one request. The six examples are functional checks with authored expectations, not a representative benchmark. Inspect disagreements and evaluate your own examples before using the label.
The window shows an error and supplies no fresh judgment. The downloadable runner sends one request without retries. Need evidence is a valid outcome about incomplete input; it does not stand in for a network or provider failure.
Edit the evidence above or use the Playground to test another bounded question.