Learn Your Way: Reimagining Textbooks with Generative AI

If you can't discern what good answers look like to the questions you're asking, you're not asking the right kind of questions.

Asking the right kind of questions is a genuine skill.

It applies to every domain of life where you are at the mercy of a "professional" or at the mercy of some knowledge differential. So you need to be a good judge of whether the answers you're getting are good answers or bad answers.

> Asking the right kind of questions is a genuine skill.

A skill we cannot rely kids to have, and which i think takes years of training and learning for even adults to really acquire. (to be clear, i'm not thinking about AI prompting. I 'm thinking about assumption breaking and understanding prodding questions the learner asks themselves and seeks answers for, to build and refine their mental models of something they learn)

> If you can't discern what good answers look like to the questions you're asking, you're not asking the right kind of questions.

Whaaaaat? How does this work? If you're trying to learn a new topic, how are you supposed to recognize a good (and truthful) answer, whether it's from an LLM or instructor?

That's absolutely not true. Kids get trained how to ask questions very quickly from a very young age. Good responses to those questions fundamentally shape the entire developmental journey for kids and extends to their academic abilities in school.

Because questions are fundamentally about knowledge differentials, which will always exist for individual human beings. We can't at any point know everything.

Know how to know what you don't know and get a good grasp of what it means to know in the first place.

Knowledge isn't absolute.

I would argue you're doing it right now.

By being skeptical of the answers, testing the answers, corroborating with other sources, etc.

This isn't new. This is literally how we've been exploring this knowledge game for thousands of years.

I would argue this isn't a fair comparison. There's a big difference between a fairly open-ended discussion about a topic both parties are at least somewhat familiar with, and someone trying to learn a new subject.

All knowledge is open ended...

I bet when you're learning a new subject you do the same exact thing.

When learning from a source like a textbook, docs, or being instructed by a person, I do not expect the source of truth to lie to me, and verify everything they tell me.

A great answer can compensate for a bad question.

A great question can compensate for a simple answer.

Kids can ask questions, but they rely on an experienced teacher to effectively answer.

Teaching someone effectively through answering questions, require the teacher through the students questions to build a model of the students model. To answer not only the question directly, but also the question that should have been asked instead.

A good end-of-chapter quiz doesn't check that a reader read the next. It asks questions whos answer rule out possible (or common) incorrect mental models the reader may have built.

A learner skilled in asking truly excellent questions, makes questions for which even a bad or simple answer rule out and refine their assumptions.

And that is a skill i doubt is ever truly mastered.

Its like the X Y. A great teacher answers X instead of Y. A great learner asks about X in the firstplace.

This. When you're reading a reputable textbook, you're not thinking all the time "wait is this true?". You trust the author to be correct and truthful.

Imagine being handed a textbook with a warning in the first page "10% of the facts here are made up (including this one). Good luck!"

Did we all just collectively forgot basic literacy?

You as the reader when you're reading anything are supposed to verify claims the author is making.

You never expect anything to be sources of truth.

That's why every textbooks either cites the sources or proves their work.

Very rarely do you have any textbook that's just a list of facts out of thin air. I don't think I've seen a single textbook, even bad ones, do this. They always cite their claims, or they show the logical steps to prove or justify a claim. Good textbooks make it easy to follow and clearly show their steps for the convenience of their readers.

Any good textbook seriously considers both the historic literature on their subject, presents the context of that literature, and shows some kind of proof of work that synthesizes all of that to support their claim.

This is always the case. This is how basic academic writing is done.

And it is the job of the reader to follow those citations, and to verify the claims. That's literally how our academic system works.

It's basic literacy.

> And it is the job of the reader to follow those citations, and to verify the claims.

How do you verify the claims? Replicate every piece of research cited?

You have a very funny definition of "basic literacy". This is (an example of) the definition most of the English-speaking world uses: https://americanenglishdoctor.com/l-2-basic-literacy/

> Know how to find information in the old technology called “books"

> Can think critically about statements made in such different contexts as advertising, entertainment, news reporting, and books written in an earlier century.

So, before indulging this any further, do you mind citing your source for the definition of "basic literacy" that includes the claim "never expect anything to be sources of truth"?

I always assume textbooks are opinionated and full of errors. I learned that to be true at a very young age. Sometimes that assumption turns out to be mostly wrong, though, and those books are rare treasures. Most schoolbooks in particular are pretty terrible.