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

New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

intextbooks.science.uu.nl

Post reply on HN
Print view View original

81–90 of 126 posts

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#81

Post by usernametaken29 »

Wow, putting effort into training material, thoughtfully designing it, and relating the material to the final exam, will increase performance on said exam. So much AI so much wow. Like seriously. Most university statistics courses suck big time, so literally any effort put into them will Improve the field. I’m happy the authors want to improve education but they don’t seem to understand that preparing questionare style material is a confounding factor which could very well explain the better performance too… instead of cramming AI into the next thing. I’m generally opposed to AI on basic textbooks. You don’t want hallucinations imprinted on students who have no idea and can’t judge the quality of the generated text. Some things require effort, reading intro to statistics is one of them, and it’s for a reason, the effort IS the learning

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#82

Post by Herring »

SgtBastard wrote: post #69
Herring wrote: post #36

Earlier quoted context omitted.

The story around Bloom's two sigma is a bit complex https://nintil.com/bloom-sigma/

Thank you for this and for parent’s comment - I know what rabbit hole I’m going down today.

Hmm, it might be better to just go straight to what leading countries currently do (Finland/Estonia/Japan/Singapore/etc). Other factors probably play a bigger role, like school funding, school autonomy, teacher professionalism (high education level + continuing education + good pay), free school meals/healthcare/transportation etc

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#84

Post by fragmede »

fn-mote wrote: post #71
fragmede wrote: post #45

Earlier quoted context omitted.

> Nobody creates cards on their phone, or while they're walking Wait, when are you doing it then? No wonder you think it sucks! Adopt some modern tools, yo. Use Anki, or vibe code your own app.

> Use Anki Anki is great for studying, but the card creation experience sucks. To be specific: I found creating any custom card type immediately dropped me into the bowels of CSS. It felt like writing HTML by hand. Is there any facility for re-using shared pieces? I felt like it needed a static site generator type tool to move up a layer of abstraction and reduce the copying of chunks into my card. Is there one? Plea…

It's rather nerdy, but QuickTurtle9 released mdfc on GitHub, https://github.com/bttger/markdown-flashcards a couple of years ago

Using that as the input file format standard, AI can generate what you're looking for, Android app, Webapp, iOS app, pdf.

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#86

Post by golem14 »

fn-mote wrote: post #71
fragmede wrote: post #45

Earlier quoted context omitted.

> Nobody creates cards on their phone, or while they're walking Wait, when are you doing it then? No wonder you think it sucks! Adopt some modern tools, yo. Use Anki, or vibe code your own app.

> Use Anki Anki is great for studying, but the card creation experience sucks. To be specific: I found creating any custom card type immediately dropped me into the bowels of CSS. It felt like writing HTML by hand. Is there any facility for re-using shared pieces? I felt like it needed a static site generator type tool to move up a layer of abstraction and reduce the copying of chunks into my card. Is there one? Plea…

> I found creating any custom card type immediately dropped me into the bowels of CSS.

Ah, LaTeX syndrome.

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#87

Post by guai888 »

Herring wrote: post #82
SgtBastard wrote: post #69

Earlier quoted context omitted.

Thank you for this and for parent’s comment - I know what rabbit hole I’m going down today.

Hmm, it might be better to just go straight to what leading countries currently do (Finland/Estonia/Japan/Singapore/etc). Other factors probably play a bigger role, like school funding, school autonomy, teacher professionalism (high education level + continuing education + good pay), free school meals/healthcare/transportation etc

One major limitation is the cost. It costs lots of money to train teachers and pay them good salaries. What leading countries are doing currently might not be sustainable for the long run. Cognitive abilities also different greatly from people to people in different discipline. There is no silver bullet.

Re: New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]

#89

Post by Robotbeat »

kubb wrote: post #13
Robotbeat wrote: post #9

Earlier quoted context omitted.

Wikipedia doesn’t make much money but is still helpful. LLMs don’t need to make a whole bunch of money to be helpful.

People aren't paying trillions to train them to be helpful. They want to make quadrillions.

Ok
Post reply on HN