A planetarium helper must accept a visitor's sky photograph and return a constellation caption. A text-only model writes prettier sentences but never sees the image. Which application-level filter should win?
Select an answer to reveal the explanation.
Short Explanation
Think of a visitor holding up a sky photo. The model has to see the picture. Prettier sentences from a text-only model still fail, and a sky photo is not audio.
Full Explanation
The application’s real input is a photograph, so the model must accept that modality. Prettier sentences from a text-only model still fail because the image is never seen. Punctuation does not add vision. A sky photo is not audio.