Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Learn Your Way: Reimagining Textbooks with Generative AI

research.google

Post reply on HN
Print view View original

61–70 of 244 posts

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#61

Post by rshanreddy »

anonfunction wrote: post #5

Shameless plug but I made a similar tool called asXiv[1] which allows you to "ask" arXiv.org papers questions. It also recommends questions on initial load that can help understand or explore the paper, here's a demo[2] from the popular Attention Is All You Need paper. The code is all opensource[3], it uses the google 2.5 flash lite model to keep costs down (it's completely free atm), but that can be changed via env…

whoa this is fantastic. wish I had known about this earlier! just made a similar product for reading arXiv / epub / pdfs called Ruminate (www.tryruminate.com), would love to hear what you think

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#62

Post by truelson »

truelson wrote: post #60

This is one of the areas where LLMs are really useful. At their core they aren’t “thinking” so much as transforming and reorienting data. What’s been most valuable for me is the way they create a kind of imperfect but effective Socratic dialogue with whatever I’m reading. I was the kid who always had my hand up in class, not to show off, but because I hated leaving something unexplained. Good teachers could make a te…

As a side note, I'm going through all the Le Carré novels... it is a lovely experience to be able to ask an LLM more questions about 1960s British culture, West German Cold War politics, and Le Carré's background as a diplomat/spy. A lovely way to engage with novels.

Also, Smiley is getting up their in fictional characters I admire. Not Iroh level, but up there.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#63

Post by criddell »

0xEF wrote: post #36
bigfishrunning wrote: post #29

Earlier quoted context omitted.

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

I was in the middle of typing the same question. This is the part that worries me about Generative AI; far too many people seem to have forgotten that its prone to confabulation and telling the user what they want to hear.

Sure, but if the LLM tells you the jump from step 2 to 3 in a calculus problem is the use of l'hopital's rule, you should be able to figure out pretty quickly if it's a red herring or not.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#64

Post by j45 »

Imnimo wrote: post #14

I looked at the example for computer science basics for a 7th grader interested in food. Explanations include: "a list can be used for a recipe" "a set can be used to list all the unique ingredients you need to buy for a week's meals" "a map can be used for a cookbook" "a priority queue can be used to manage orders in a busy restaurant kitchen" "a food-pairing graph can show which ingredients taste good together" May…

This is a start, not the end.

Instruction and instructors won't be going away.

Most people have never looked at textbooks needing evolving.

It's like the LLM ai shift to not think about how software used to be.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#65

Post by yorwba »

cadr wrote: post #8

I feel like this is thinking too small. I don’t want a better textbook. I want them to be basing this off of the experience of going to the most effective private tutors.

The textbook is there so that the model has something reasonably correct to work with and doesn't make up too much wrong stuff to teach.

For tutoring, I think the approach in https://www.nature.com/articles/s41598-025-97652-6 is promising. (Prompts are included in the supplementary material on the last page: https://static-content.springer.com/esm/art%3A10.1038%2Fs415... ) They start with an existing collection of worked exercises, give the chatbot access to the full solution and then let students interact with it to get a walkthrough or just check their own solution, depending on how much help the student thinks they need.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#66

Post by cjs_ac »

SJMG wrote: post #51
cjs_ac wrote: post #10

I'm a former physics teacher, and while I'm impressed by the technology, I think this is a low efficacy innovation. The real challenge in teaching Newton's laws of motion to teenagers is that they struggle to deal with the idea that friction isn't always there. When students enter the classroom, they arrive with an understanding of motion that they've intuited from watching things move all their lives, and that under…

> the head of languages telling me that a good teacher can teach any subject. Tell me this wasn't foreign languages? :face_palm: Okay, I was totally with you until this, > but I think we've got everything we can out of the subject-agnostic approach to improvement, and we need to start engaging with the detail of what's being taught to further improve I think if you walk into the bottom 80% of classrooms you would not…

> I think if you walk into the bottom 80% of classrooms you would not see, interleaving, spaced repetition, recall-over-reread, or topic shuffling to avoid interference.

Where have you taught? I taught in Australia and the United Kingdom, where many of these things were mandated by the promulgation of spiral curricula by the relevant government departments. I'm aware in the US that, for example, algebra is taught as one or two block courses, but in the school systems I've taught in, algebra is taught as a few 'topics' of about a month in duration each, sprinkled throughout the whole four or five years in which mathematics is mandatory in secondary school. For Year 7 to 10 in Australia, there would be one or two topics for each of physics, chemistry, biology and earth sciences, covered across each year, building up from year to year. None of this was a choice by individual teachers or even schools; it was an artefact of the way the curricula are structured.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#67

Post by ycombigators »

cjs_ac wrote: post #10

I'm a former physics teacher, and while I'm impressed by the technology, I think this is a low efficacy innovation. The real challenge in teaching Newton's laws of motion to teenagers is that they struggle to deal with the idea that friction isn't always there. When students enter the classroom, they arrive with an understanding of motion that they've intuited from watching things move all their lives, and that under…

You should have asked the head of languages to teach you tensor calculus.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#68

Post by zhyder »

Plug for our https://uphop.ai/app : it's for adult learning / corporate training. We break down a desired job skill into small chunks, and engage the user with practice & give nuanced feedback. And of course like chatbots make it easy for user to ask more questions or go on tangents.

Would appreciate feedback!

There's a bit of overlap with Learn Your Way I guess. I'm not sure users need to toggle between alternate formats of the same instruction though. Instead the instruction itself should be as multi-modal as possible, and offer flexibility to ask questions... which even gemini.google.com offers so I'm not sure this is a net improvement over that.

Re: Learn Your Way: Reimagining Textbooks with Generative AI

#70

Post by einpoklum »

1. Much of this suggestion has nothing to do with AI. Offering learners alternative forms of media for a subject is interesting and probably useful, regardless.

2. About the AI part: Let's remember that at the other end of these bells and whistles there is a huge amount of expended electricity, and sprawling sever farm infrastructure. That's the hidden cost. For now, it might seem like someone else is footing the bill, but that will not last for very long - and in fact, it already starting not to last. See:

https://www.newsweek.com/ai-data-centers-why-electric-bill-s...

A typical US household is paying a 26 USD "AI tax" this year through its electricity bill.

Post reply on HN