A topic, study notes, or a script. You can also add PDFs, images, audio, and video you have permission to use.
AI explainer video generator
Turn your topic, study notes, or script into a narrated video.
Loading your studio…
Create on desktop. Watch examples on any device.
Made with AhaNow.
Explore styles ↗How LLMs Actually Work
1 min 32 secEverything Starts with a Question
30 secTranscripts & video notes
How LLMs Actually Work
A visual explanation of large language models. Watch how the subject is broken into scenes.
Most of us picture a language model as a kind of search engine. You ask a question, it looks up the answer somewhere inside and hands it back. That picture is wrong, and it is wrong in a way that explains almost everything else about these systems. Here is what actually happens. The model reads everything you have given it and produces a probability for what should come next. It picks one, adds it to the text, and starts over. Word by word, that is the whole machine. To do that, text has to become numbers. Sentences are broken into small pieces called tokens, and each token becomes a long list of numbers. Meaning, in this world, is a position in space. Close words sit close together. The model learned by exposure. Show it an enormous amount of text, hide the next token, let it guess, and measure how wrong it was. Then adjust billions of internal weights, slightly, so the next guess is a little less wrong. Repeat that across trillions of words. Nobody wrote the rules. What emerged was a compressed sense of how language and ideas fit together. So when the model sounds like it knows a fact, it is not retrieving it. It is reconstructing something plausible from patterns, which is why it can be fluent and false at the same time. That is the mental model worth keeping. It is not a database, and it is not thinking the way you do. It is autocomplete at a scale that makes it feel like understanding. Once you see that, you know exactly when to trust it, and when to check.
Everything Starts with a Question
A short motion-design study using Google’s visual identity. An independent concept, not a Google endorsement or customer story.
Music-only concept film. On screen, a search for the distance to the moon becomes a map journey, a calendar, and a ring of tools. The closing text reads: Everything starts with a question.
- 01
Bring an idea
Add a topic, script, or reference files.
- 02
Shape the story
Review the script, choose a style, and refine the scenes.
- 03
Make it yours
Generate, revise, and export your video.
Yes. Refine the script, visuals, and pacing. Changing spoken words requires regenerating the voice; editing captions alone does not change the audio.
An MP4 video, or a ZIP with an FCPXML timeline and media. Visual effects are baked in, not a fully layered motion-design source project.
Planning, generation, and revisions use credits. Review the estimate before generating. Trial allowances depend on your account; a first-scene preview is not a free complete video.
Create on a computer with a browser at least 1024 pixels wide. You can watch examples on any device.