Turn long video lectures into true mastery

Paste a YouTube link. Ritsu reads the whole lecture, cuts it into bite-size concepts in the order they build on, and turns all of them into a Knowledge Map to learn from in seconds — until you master the dense content of the video.

A 20-second product loop: a document becomes a step-by-step learning path in Ritsu.

The illusion of having learned

Watching didn't work. Watching again won't either.

With a book you at least close it and try to remember. With a video, the only thing to do is play it again — the same passive hour, a second time. The cure is the disease.

You watched the whole thing. At 2×, so it took an hour, and it felt efficient. You nodded at the right moments. You may even have taken notes.

Then three days later someone asks what the lecturer actually said about it, and you have nothing. You can't retrieve from a video. You can only re-watch it — and re-watching is the same passive hour with a different feeling attached. Playback speed is the most seductive fake-productivity setting ever shipped: it makes two hours feel like an hour of work. It is one hour of watching.

There's only one way out: stop pressing play. Start being asked.

The workflow

From two hours you sat through to concepts you can produce.

01

Paste the link

Any lecture you can watch, you can learn from. Nothing to download.

Lecture 4 · Training Neural Networks01 / 06
youtube.com/watch?v=…paste
02

Two hours, cut into concepts

Ritsu reads the whole lecture and breaks it into bite-size concepts — wired in the order they build on. The two-hour blur becomes a list of things you can actually hold.

Lecture 4 · Training Neural Networks02 / 06
03

The bit that lost you, from another angle

A lecture runs at one speed, and it isn't yours. When it lost you, you don't need to re-watch the ten minutes before — you need the idea explained differently. /eli5, /analogy, /intuition: another angle, no rewinding.

Lecture 4 · Training Neural Networks03 / 06
/eli5/analogy/intuition· no rewinding
04

Now it asks you

/quiz on the concept, not on the video. Retrieval practice — the most proven way to make it stick. Pull it back out, cold.

Lecture 4 · Training Neural Networks04 / 06
/quizon the concept, not on the video
05

Explain it back

/askme is the thing a video can never do. It talks; you listen. This reverses it: you explain the concept in your own words, and Ritsu names exactly where your explanation broke.

Lecture 4 · Training Neural Networks05 / 06
/askme“…so the gradients blow up in deep nets?”

They vanish — and Ritsu names exactly where it broke.

06

Keep it past the forgetting curve

Ritsu brings each concept back right before you'd forget it. Master the lecture today, still own it on exam day.

Lecture 4 · Training Neural Networks06 / 06
review dueWeight init — right before you'd forget it

Pedagogy, packaged

Every command packs a proven learning method.

Pick any concept off the timeline. Six commands take it from “I remember him saying it” to “I can write it from memory” — each one asking more of you than the last.

Vanishing gradients
/explain01

Understand

The core idea first, then the layers — built from the lecture you just watched.

/quiz02

Recall

Retrieval practice: the most proven way to make it stick. Pull it back out, cold.

/flashcard03

Drill

The parts that have to be automatic, turned into cards you'll actually run.

/askme04

Explain back

The Feynman test. Say it in your own words — that's where the gaps show.

/exercise05

Apply

A real problem on the real concept. Knowing it and using it aren't the same.

/write06

Create

Write it out in full. The highest bar there is: if you can write it, it's yours.

That's Bloom's taxonomy, climbed one command at a time. And the science isn't a slogan — it's a flag on the command:

/quiz --bloom="auto"

40+ commands, all built like this.

Knowledge Map

You always know exactly where you stand.

A progress bar tells you how much of the video you've watched. It has never once told you what you know. Ritsu scores every concept as you work — the dim ones are exactly what you haven't got yet.

Lecture 4 · Training Neural Networks · Knowledge MapScore 64%
masterednot yetreview due
01

Every concept, scored.

Not one vague % for the lecture — a mastery score per concept.

02

Dim = what will bite you.

The concepts you haven't got yet, named. That's the list nobody else gives you.

03

Two hours, one screen.

No more scrubbing to find the bit you need — the map tells you.

Spaced review

Master it today. Still have it on exam day.

You forget most of what you learn within days — Ebbinghaus measured it in 1885. Ritsu brings each concept back right before it fades, so the work you did today is still there when it counts.

100%50%0%day 01234567reviewreviewreviewWithout review: gone in a week.With Ritsu: every review resets the curve.

Five minutes tonight. Three tomorrow. Two in three days. Built from your lecture — no cards to make.

When you're stuck

The moments you actually get stuck — and what to type.

You don't need the ten minutes again — you need the idea from a different angle. /eli5 → /analogy → /intuition — a lecturer has one way of saying it. Ritsu has as many as it takes.

Lecture 4 · Training Neural Networks

two hours, mastered piece by piece

Stop pressing play. Start producing.

Free forever · no card