How we keep videos accurate
A short video about how Explain a Paper keeps a video true to the paper: an AI video model paints every frame from patterns, not from your data, so its text, numbers and charts can come out wrong, as independent tests and its makers' own reports say, and as our own test showed; our specialised AI agents draft the script, you edit and approve it, and our software draws every frame, with typeset words, charts plotted from the paper's own numbers and a synthetic narrator; and the measured energy of a whole video.
Transcript
Ask an AI video model for a chart from your paper, and it paints something that looks like one: from patterns, not from your data. To it, letters are shapes, so words come out garbled; a number only has to look right; and nothing ties its chart to your paper. Independent tests, and their makers' own reports, agree. When we tried one, it spelled the author Eovin Hubble, wrote expllinapaper dot com, and its chart had none of Hubble's data.
What we do instead: our specialised AI agents draft the script, and you edit and approve it. Then our software draws every frame: typeset words, charts plotted from the paper's own numbers, diagrams in code. A synthetic narrator reads it. So every word, number and chart comes from the paper and the script you approve.
A whole seventy-second video, drafting included, used about fifty to ninety watt-hours when we measured it in September. One take of AI-generated footage used one point seven kilowatt-hours. Try it yourself: get started today at explainapaper.com.