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

(intextbooks.science.uu.nl)

55 points | by jonahbard 2 hours ago ago

28 comments

  • KaiserPro 3 minutes ago

    I'm not an expert, but how much of this is down to novelty, ie https://en.wikipedia.org/wiki/Hawthorne_effect ?

    (ie changing the environment can lead to short term productivity gains because either participants are aware they are being watch, or it breaks up the monotony and makes people work a bit harder. )

  • rictic 6 minutes ago

    Yes! Very exciting to see this.

    Bloom's Two Sigma Opportunity suggests that there's another SD improvement available: https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem

  • baq 43 minutes ago

    I'm on record saying that a system like this with some extra hardware (i.e. a way for the LLM to have live understanding of the student's paper notebook or handout which are being written in with a plain old pencil) combines the best of both worlds - individual tutoring with approximately zero screen time which scales linearly with the number of students. The role of the teacher or professor then becomes a manager of the student - agentic tutor pairs, a referee when the student and model disagree, etc. and most importantly still being the human teacher you can just talk to in the human education process.

    I'm convinced this is the future of education - models are there, we need the classroom tech to catch up. The alternative is obvious and quantified in the paper - students just use models to do their work for them and learn nothing.

    • terribleperson 18 minutes ago

      A 'smart pen' that records the student's writing in some way, maybe? My first thought was a tablet that boots straight into a writing software but students should not be subjected to any amount of latency in their writing.

      Practically, I think if you want the AI system to have a live view of what the student's doing you're going to have to replace one of either the tablet or the writing instrument. A wearable camera could work as well but there are issues with that.

      • 1bpp 2 minutes ago

        Would a modern accellerometer in a pen + ML model be sensitive enough to reconstruct letters written?

      • universa1 7 minutes ago

        there was a pen that used special paper to directly record your notes (15-20years ago)... should be possible nowadays to directly transfer this to a connected device and have it feed it to an llm.

        and after looking it up, it appears they are still available: https://www.livescribe.com/landingpage/ls3_onenote/

    • Buttons840 17 minutes ago

      I would add that somewhere in there should be a spaced repetition algorithm.

      Spaced repetition is very effective, but it's really really clunky to use. My unpopular opinion is that we all have Stockholm syndrome when it comes to creating "cards", and people talk about how valuable creating cards is; but I think it stucks, it takes a lot of time.

      If AI is already teaching me math (let's say), it would be nice to tell the AI/app "quiz me on this periodically", and then the AI makes up a fresh polynomial to factor (or whatever) and presents that to you according to a spaced repetition algorithm.

      Behind the scenes, the AI should have access to what has happened the last several times a specific topic has been quized, so the AI can watch to see that certain mistakes are resolved, and the AI might also know better how to correct the user if it has context about previous quizzes of that topic.

      • tired-turtle 12 minutes ago

        But the very act of making and organizing your card deck is part of the SRS! It “sucks” because you get no dopamine hit from a fresh desk, as the reward system is not yet in place.

  • mmarian 35 minutes ago

    Conflicted about this study. On one hand, LLMs have been incredible for my personal learnings of new concepts.

    On the other, I'm sceptical of that it'll have "strong benefits" at scale; I'd be more in favor if the wording was "some"/"moderate". I reckon self-selection plays a huge part, as mentioned in the "Limitations" section of the paper.

    I'd also caution against attaching the tool to grading. That means students have to put more effort into the course, which increases the chances that they will use LLMs to save time rather than make the investment.

  • rusbus an hour ago

    This is exciting because the effect size is so large. But as the author's acknowledged, selection bias is nearly impossible to control for in this non-randomized study:

    > and lacks randomized controls. Self-selection is the central threat: students who complete more quizzes may be more motivated or higher-performing generally

    But this is still a strong result. I'm excited to see more in this space.

    • rahimnathwani 25 minutes ago

      They tried to control for this. It's described in the first paragraph of section 4.

  • boulos an hour ago

    Do you have a larger study planned for the Fall? It definitely seems promising.

    I'm curious how well you feel this worked because the subject was Statistics (objective grading) versus something more subjective like Civics or Literature.

    PS - I'd say this qualifies for Show HN, too!

    Do you

    • ilaksh an hour ago

      They were using Sonnet 4.6 for some fre form responses so that could be applied to something subjective.

  • Rperry2174 an hour ago

    Honestly whether or not this was effective seems less important to me than the adoption numbers.

    Text book reading in this course was 10-15% at baseline ... but this AI thing got 90% voluntary usage ungraded.

    Even if its worse per-hour than a textbook, you're now teaching 6x as many students _something_ instead of teaching a small minority everything.

    So really it just becomes an optimization problem at that point because most students are at least in the funnel/in the running to learn something.

    The paper kind of proves this itself ... they tweaked the quize formats mid-semester and where able to iterate which you can't do on a textbook that nobody opens in the first place

    • baq 41 minutes ago

      I'd argue the results are even better: just reading a textbook doesn't really teach you much. You have to do exercises, but they're expensive to create and grade. LLMs with a proper harness (see paper) tackle both.

  • MoneyBurning 25 minutes ago

    Curious how this holds up across different learning styles. SD effect sizes look impressive, but I'd want to see retention data at 30/90 days before drawing conclusions.

    • isomorphic_duck 22 minutes ago

      Why did you make a new account to spam AI comments?

  • constantius an hour ago

    Interesting, congrats.

    Are you planning on opening access to Phosphor?

  • kubb an hour ago

    Too bad the educational use case doesn't make any money. Good LLMs are a game changer for people motivated to learn.

    • jasondigitized 8 minutes ago

      Not sure if its education, but there is huge money in the college admissions process, e.g., SAT prep.

    • TheLML an hour ago

      I don't want to learn from hallucinations where it will change its answers based on me questioning their teachings. I use it for conversations in a language I'm learning, but I quickly learned that asking it grammar questions for example is not a wise decision.

      • treis 33 minutes ago

        Are we talking about human teachers or LLMs here?

      • afro88 38 minutes ago

        Curious whether you were just bare asking it questions, or whether you provided it with lessons one by one with instruction that the lesson is the baseline truth etc

    • Robotbeat an hour ago

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

      • kubb 39 minutes ago

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

  • albinahlback an hour ago

    Very nicely typeset.

  • ilaksh 38 minutes ago

    Shocking that a well executed AI tutor improves outcomes.

    Hasn't computer assisted interactive learning already been proven for years? Why does there seem to be so much skepticism about enhancing it with AI?

    Is this just something like, astoundingly slow adoption or poor execution? Being held back by paper textbook makers? Teachers unions dragging their feet?

    How can interactive AI driven individually paced learning _not_ be obviously dramatically more effective?

    • dominotw 37 minutes ago

      its like anything else. benifits students that are already motivated to learn.

      very few are actually motivated to learn and are just there to get a job or its just next thing that they have to do in life.