Skip to content

BeginnerLesson 2 of 57 min read

Multimodal: when it sees and hears

A course from the Academy: They are not all the same.

Go to the quiz ↓

"Multimodal" simply means it accepts something other than text. The word is jargon, but the consequence is very concrete.

What it really enables

A photo. Snap a picture of a manual, an oven plate, a form, a chart on the wall, and ask it to explain it. This is the use that surprises people the most, and the most immediate.

A document. A forty-page PDF, a spreadsheet. It reads it, and you extract whatever you want from it.

Voice. Speaking instead of typing, and sometimes listening to it reply. Decisive for those who type slowly.

What to know before relying on it

On a photo, it reads clear printed text well. It struggles with handwriting, a blurry photo, or a dense table of figures. Above all: it makes the same transcription errors as with text. Any amount read from an invoice must be checked.

Long documents

On a document of several dozen pages, it tends to handle the beginning and end well, and skim over the middle. For serious reading, break it up: chapter by chapter rather than all at once.

What to do now

Photograph the manual of a device you've never fully understood and ask it for the three things you need to know.

Key concepts

Complete the lesson

A 4-question quiz: 3 correct answers are enough, plus an exercise to practise. It opens in the Academy, on this same lesson.

Take the quiz and complete the lesson Free. With an account, your progress is saved and leads to the course certificate.

The course: They are not all the same.

  1. Quick or considered: two families8 min
  2. Multimodal: when it sees and hears7 min
  3. The context window: its working memory7 min
  4. Open or closed: what it means for you7 min
  5. Choosing in practice, in three questions6 min

The whole Academy →The AI glossary