←back to thread

Learn Your Way: Reimagining Textbooks with Generative AI

(research.google)
359 points FromTheArchives | 2 comments | 18 Sep 25 17:42 UTC | HN request time: 0s | source
Show context
oceanhaiyang ◴[18 Sep 25 19:08 UTC] No.45293700[source]▶
No one who understands ai can rely on it to help us learn. I provided one with 100 citations I wanted to standardize and it deleted 10 and made up 10 to replace them. Can’t imagine this being used to replace a textbook or even explain a textbook.
replies(3): >>45293802 #>>45294049 #>>45296961 #
criddell ◴[18 Sep 25 19:17 UTC] No.45293802[source]▶
> explain a textbook

I've had very good luck using LLMs to do this. I paste the part of the book that I don't understand and ask questions about it.

replies(3): >>45293911 #>>45293968 #>>45294577 #
bigfishrunning ◴[18 Sep 25 19:28 UTC] No.45293911[source]▶
But the problem is, you don't understand the passage, so therefore how will you vet the answers? Seems like hallucinations would be very very damaging in this use-case
replies(4): >>45294006 #>>45294052 #>>45294616 #>>45295154 #
lacy_tinpot ◴[18 Sep 25 19:41 UTC] No.45294052[source]▶
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.

replies(2): >>45295186 #>>45295214 #
squigz ◴[18 Sep 25 21:28 UTC] No.45295214[source]▶
> 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?

replies(1): >>45295299 #
lacy_tinpot ◴[18 Sep 25 21:35 UTC] No.45295299[source]▶
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.

replies(1): >>45295376 #
squigz ◴[18 Sep 25 21:42 UTC] No.45295376[source]▶
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.
replies(1): >>45295473 #
lacy_tinpot ◴[18 Sep 25 21:52 UTC] No.45295473[source]▶
All knowledge is open ended...

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

replies(1): >>45295501 #
squigz ◴[18 Sep 25 21:55 UTC] No.45295501[source]▶
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.
replies(2): >>45296037 #>>45296588 #
1. ares623 ◴[18 Sep 25 22:57 UTC] No.45296037{3}[source]▶
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!"

replies(1): >>45299659 #
2. a96 ◴[19 Sep 25 09:26 UTC] No.45299659[source]▶
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.