[HN Gopher] One AI Tutor Per Child: Personalized learning is fin...
___________________________________________________________________
One AI Tutor Per Child: Personalized learning is finally here
Author : ChaitanyaSai
Score : 263 points
Date : 2023-03-17 14:52 UTC (8 hours ago)
(HTM) web link (saigaddam.medium.com)
(TXT) w3m dump (saigaddam.medium.com)
| yalogin wrote:
| In India there is already a big push towards getting every kid a
| computer in the government run schools. There are huge companies
| that deliver computers and then also the teaching/lessons
| services on top. Now they are also going to latch on to the AI
| story to make money. Nothing more to it. Meanwhile on the ground
| teachers are treated like dirt, over worked and under staffed.
| mynameisvlad wrote:
| You make it sound like improving childhood computer literacy is
| somehow a bad thing.
| tablespoon wrote:
| We've seen this before: use hype and techno-optimism to sell a
| bill of goods.
|
| If history is any guide, the concept of an "AI tutor" won't be
| used to "[give] every child their own personal Aristotle," it
| will be used to cut costs by replacing human teachers for low-
| status students with poor substitutes.
|
| Seriously, think about how much money can be saved from firing
| most teachers and locking poor kids in a cubicle farm to stare at
| an insane "AI tutor's" screen all day.
|
| And what's the strongest message sent by replacing human
| interactions with a machines?: "We don't care enough about you to
| actually bother to interact with you." Think of how you feel when
| you have a problem, you make a call to fix it, and all you get
| are phone menus.
|
| And look at all the examples in the article: use GPT to generate
| crappy stories and educational games for kids to play. How can
| anyone think that's better than using a book? At least the book's
| stories and games can be tested and evaluated before use.
|
| The actual problem here is the sociopolitical one of
| unwillingness to allocate enough resources to education to make
| it truly effective and satisfying, and that's one that technology
| can't solve.
| A4ET8a8uTh0 wrote:
| It is actually an interesting point. Journalists seem to be
| catching up to the fact that running ( or at least training
| data ) is not exactly a cheap task and kids aristotle probably
| shouldn't be trained on 4chan.
|
| Naturally, some analysts would say that means there is tons of
| consulting money to be made..and it seems like spending is easy
| and profitable.
| stephenhuey wrote:
| And the divide may further increase since kids whose families
| can afford personal human instruction may get ahead even more.
| nabnob wrote:
| Well fucking said. For a lot of kids, their teacher is one of
| the few stable adults in their life. There's a ton of social
| and emotional things kids learn from good teachers beyond just
| book knowledge.
| forgotusername6 wrote:
| Though there are plenty of people who could provide the
| social side but aren't equipped to teach the curriculum.
| Perhaps you could use an AI teacher to deliver lessons that
| the class teacher was not qualified to teach. This could be
| done with the real teacher in the room.
|
| One of the best teachers my child ever had was limited to
| teaching first grade due to a lack of maths ability.
| Everything else about them was fantastic. Maybe AI teachers
| can help in cases like that.
| kwhitefoot wrote:
| There are plenty of people who can do the technical side of
| teaching the curriculum. Most of them can earn more
| elsewhere doing a job that is considerably less stressful.
| Education needs to be funded so that it can attract people
| and it needs to be reorganized to reduce the stress.
|
| The vast majority of what is taught in primary schools
| doesn't need a lot of subject matter skill, what it needs
| is the ability to teach and the toughness to survive the
| environment. And it has to pay well enough to attract
| people who have those qualities because those same
| qualities make those people attractive to other employers.
| fn-mote wrote:
| > There are plenty of people who can do the technical
| side of teaching the curriculum. Most of them can earn
| more elsewhere [...]
|
| Yes.
|
| One problem I come across repeatedly is: how do you
| identify whether someone has the technical competence to
| do the teaching? Is there any way of knowing if they're
| doing a good job?
|
| As an IC they are implementing features and shipping
| products. As a teacher...? Test scores going up is
| uncorrelated with teaching quality, apparently. (NYC,
| just look at the scatterplot in [1].) So it seems like
| there's a deep problem here.
|
| Now imagine someone in K-12 hiring a CS teacher. Who do
| they have that is competent to evaluate the skills of the
| person they want to hire? Probably nobody at all.
|
| [1] https://garyrubinstein.wordpress.com/2012/02/28/analy
| zing-re...
| nextworddev wrote:
| Not sure if an AI tutor is a "poorer" substitute for ALL human
| teachers given there are many teachers who aren't be try
| qualified teaching
| ren_engineer wrote:
| >it will be used to cut costs by replacing human teachers for
| low-status students with poor substitutes
|
| most public school teachers are glorified babysitters at this
| point anyway, I can recall only a single teacher during my 12
| year public school attendance that was actually helpful. From
| what I've seen from GPT-4 so far, I'd have taken a ChatGPT Plus
| subscription and laptop over dedicated teachers. YT and Khan
| Academy were far more useful than my actual teachers
| idontpost wrote:
| [dead]
| cyrialize wrote:
| I've mentioned this before across HN, but I'll mention it
| again - human-to-human interaction is critically important
| for young children.
|
| You basically have to teach young kids how to act like a
| human being. Kids will get this teaching in daycare and
| through their parents, but that alone isn't enough and it is
| important to reinforce this through schools.
|
| People often forget this because you don't really remember it
| and then you end up making assumptions on how you act now -
| not realizing that a teacher may have taught you when you
| were younger.
|
| I think the best example of this is handing out worksheets to
| kindergartners. An average person may think that you just
| give them pencils and paper. An experienced teacher knows
| that they have to teach the kids where to write their name,
| how to follow along the line, to read instructions, flip the
| page over to check for more, etc.
|
| This is practically true for all children. Again, many may
| argue that you can receive this teaching through your parents
| and day-care, but once a child gets old enough they are
| spending most of their time in school. Think of it like
| language learning. You'll learn more of the language if you
| are being taught it all day, rather than only at home with
| your parents.
|
| You also experience more interaction with kids your age at
| school. There are many situations that come up where a
| teacher guiding you is important, and these same situations
| may not come up at home (especially if you are a single
| child).
|
| I do think after a certain point you can rely on technology
| more for learning. I just want to emphasize that having a
| human teacher trained for working with children is critically
| important for the growth of a child.
| agentdrtran wrote:
| teachers do not _want_ to be babysitters, but when you have
| overstuffed classrooms, no prep time, no equipment, hungry
| kids, etc etc what are you able to do?
| dmvdoug wrote:
| Not to mention state-mandated testing regimes that have
| nothing to do with actual student learning, hyper-local
| control of education in elected school boards whose members
| are often as dumb as a box of rocks, extreme pressure from
| administrators to get kids through so their performance
| numbers are juiced rather than actually taking whatever
| time is needed for those students to accomplish what they
| need to, etc. I'm a public school teacher. I never cease to
| be impressed how very little people who don't work in
| education understand about the realities of education.
| HDThoreaun wrote:
| I don't see what point you're trying to make. Sure, we
| could make education better by spending more on it, but the
| voters don't want to, so it's not going to happen. Given
| that society is not willing to spend more on education what
| can we do with the budget we have?
| _justinfunk wrote:
| I think we've tried the "we could make education better
| by spending more on it" method. Based on the current
| state of public education, I don't know that this
| approach has been proven correct.
| fn-mote wrote:
| 1. Citations for the claim that we are spending more for
| the same results would be productive... but I believe it.
|
| 2. I believe the problem is that the extra money is not
| going to proven-effective programs and teachers. There is
| some question to me whether anything is proven
| effective... in spite of whatever you read in books
| written for teachers.
|
| 3. The parent comment is pretty nihilistic. Try to
| propose something that you think might improve the status
| quo. (E.g., the comments about the highest impact of
| extra spending being in social services instead.)
| HDThoreaun wrote:
| > Try to propose something that you think might improve
| the status quo.
|
| Use LLMs to compliment class activities so that students
| can receive the individual attention they need.
| lm28469 wrote:
| Did you do an AB test with your clone and checked how it
| fared without going to school ?
| tablespoon wrote:
| > most public school teachers are glorified babysitters at
| this point anyway
|
| That's a common but pretty twisted bit of logic: "we've made
| it shitty, so we should make it shittier because it's already
| so shitty."
| savanaly wrote:
| No, he said we should make it less shitty. And outlined a
| way to do so. Why misrepresent his words?
| tablespoon wrote:
| > No, he said we should make it less shitty. And outlined
| a way to do so. Why misrepresent his words?
|
| No, he didn't outline a way to make it better. He
| denigrated the people involved, in a way that is (most
| charitably) an oblique reference to low education budgets
| (e.g. not enough money to hire enough teachers or attract
| talented teachers). Then he held up some references to a
| few techie things.
|
| Maybe he's a genius autodidact that never really got much
| benefit from his teachers. There have always been people
| like that, but they've never been common. A system
| tailored to people like that would fail the vast majority
| (e.g. be shitty).
| kwhitefoot wrote:
| Sounds like you were self motivated. What about all the other
| children who have been told over and over that scholastic
| achievement is only for the weak and those whose early years
| were spent gazing vacantly at television. A teacher's job is
| not merely to recite the material but also to somehow make
| the student receptive to it.
| ajot wrote:
| > We've seen this before: use hype and techno-optimism to sell
| a bill of goods.
|
| Yep, after reading a piece on ed-tech failures of the decade
| 2010-2020[0] here on HN[1], I've become pretty convinced that
| big-scale education is hard (if not impossible) to solve with
| IT might only.
|
| Sure, one person alone can learn something through Wikipedia,
| Coursera, YouTube, Khan Academy or tutorials, but that can't
| replace structured environments if your missiob is to educate
| lots of people.
|
| [0] http://hackeducation.com/2019/12/31/what-a-shitshow
|
| [1] https://news.ycombinator.com/item?id=21948132
| imchillyb wrote:
| > ..."We don't care enough about you to actually bother to
| interact with you."
|
| "Thank you for calling customer support. We value your
| business. Please enjoy this...music...while you wait. Thank you
| for calling customer support." M U S I C ! ! !
| UncleMeat wrote:
| I'm very worried about this.
|
| We spend an absolute shitload of money educating children. This
| is paid for by society. But it is also _so incredibly worth
| it_. I 'm worried that politicians will see an opportunity to
| shed costs without considering the implications and we end up
| with children raised online by robots.
| motoxpro wrote:
| Very US centric point of view. If the teachers are fine, leave
| them be. If a place doesn't have the resources to hire said
| teachers, use tools that help.
|
| Or in the US, if teachers are that important, maybe give them
| more resources to do their job. i.e. buying supplies,
| computers, etc for your kids class.
| andybak wrote:
| I'm cautiously more optimistic. Education is already
| chronically underfunded in most places. If it became cheaper to
| give personalized attention then maybe the quality of education
| delivered might actually improve.
| tgv wrote:
| It won't. You don't get attention; you get a reply.
|
| MOOCs have terrible performance in comparison with even huge
| audience lectures. Online teaching during COVID proved that
| that doesn't work either. A machine doesn't have the
| authority and conviction of a real person. The combination
| means that the levels will have to drop only to sustain the
| idea that this could work.
|
| If some country is going to push this, the sunken cost
| fallacy and the impossibility to hire new teachers will
| finish education off, once and for all.
|
| Optimism should _NEVER_ be a basis for fucking with something
| as important as school.
| ghaff wrote:
| I'm not convinced a MOOC is necessarily worse than a pure
| large lecture class if the material is amenable to auto-
| graded problem sets. (Leaving aside a regular class would
| typically have TAs and other students you could get help
| from.)
|
| But they sure didn't live up to the hype. They didn't
| democratize education in any meaningful way. And I'm not
| sure even the people with undergrad and grad degrees who
| made up the majority of MOOC students use them much these
| days. I know, for me, they were mostly a novelty for a
| while. Maybe if I want to dip into a topic I'll watch some
| online video but I haven't even signed up for a MOOC for
| years at this point.
| objektif wrote:
| I would spend insane amount of money if AI can educate and
| entertain my kids.
| japhyr wrote:
| This kind of conversation always comes back to the tension
| between school and learning. Everyone agrees learning is a good
| thing; school has been a mix of really good experiences, okay
| experiences, and traumatic experiences for people.
|
| Think back a moment to the best teacher you ever had. Many of us
| have had a teacher who was so good, they affected the trajectory
| of our lives for the better.
|
| I'm much more careful in how I phrase experiences with bad
| teachers, because there are teachers who have assaulted people.
| Fortunately, the worst teachers I ever had were just terrible at
| teaching; they were protecting their jobs more than teaching, and
| we just had to endure a semester with them and try to not let
| them tank our grades. Mostly we laughed at them behind their
| backs and spent that time socializing.
|
| I have a 12yo. I would much rather he spend time with an AI tutor
| than endure time with one of these bad teachers. But I also,
| _really_ don 't want him to miss out on those life-changing
| experiences with some of the best teachers around.
|
| Like all things in life, it's all about balance. These AI tutors
| are just new tools, and we need to figure out how to use them
| well in our human lives.
| ranting-moth wrote:
| If you thought your schooling was boring, imagine being stuck
| with the woke ChatGPT as a tutor for 10 years.
| nerdponx wrote:
| It's astounding that you are so fearful and narrowminded as to
| think ChatGPT being "woke" is the problem here.
| ranting-moth wrote:
| I'm more fearful of how difficult it is to discuss problems
| with woke people due to their tendency to make it personal
| and belittling people they disagree with.
| nerdponx wrote:
| Everyone else is here debating AI and education. Nobody
| said anything about being "woke" except you.
| nemo44x wrote:
| I'm sure there will be a based model as well.
| enobrev wrote:
| At this stage, I would sooner give my toddler an all-access pass
| to YouTube.
|
| I'm not saying this will _never_ be good. But it feels pretty
| early to unleash this bastion of confidently incorrect answers
| upon developing minds.
| snickerbockers wrote:
| My $0.02 is that this a very dangerous idea with the current
| state of GPT. My experience with ChatGPT is that it has a
| tendency to make up bullshit when it doesn't have the answer to a
| question instead of admitting that it doesn't know, and that's an
| extremely bad example to set for children.
|
| Maybe some day this could happen; it probably is possible to make
| a language model that isn't an arrogant jerk, but it needs to be
| thoroughly tested first.
| gaze wrote:
| My partner, who works at a school, shared an email with me this
| morning that said "We just received 15 cases of copy paper. This
| has to last us to the end of the year." Usually when you try to
| make an honest effort to improve things, you make a ranked list
| of things that will have the most impact, not a ranked list of
| things that will be the most entertaining to you. I wonder if
| these people who think this is a good idea have polled the
| teachers to see what they think of the idea. I get that part of
| the silicon valley ethos is "we know best" but come on -- is the
| "if we gave people what they asked for, they'd get a Zune"
| approach appropriate for education, when the flaws are so
| glaringly obvious?
|
| The teachers and schools need more money that goes to teachers
| and student resources, not more iPads, smartboards, bullshit-
| artist AI, or overinflated admin salaries. Just call this what it
| is -- entertainment for technologists.
| tablespoon wrote:
| > I get that part of the silicon valley ethos is "we know
| best"...
|
| It's not even really that, because phrasing doesn't really
| capture how off-target and self-serving SV often is. It's more
| like "whatever we happen to be hyping right now is your
| solution."
|
| > Just call this what it is -- entertainment for technologists.
|
| That's spot on.
| moron4hire wrote:
| Considering the massive amount of resource expenditure that it
| has taken to develop LLMs, is this really cheaper than just
| giving kids a tutor?
|
| I work in adult education, at a company that services government
| contracts. We keep hearing about how our clients are dreaming
| about AI making the "perfect" learning experience for their
| employees, customized to their every need.
|
| Or at least, that's what they say. They say they want customized
| experiences for students, but what they really mean is they want
| to cut costs. Because if it was just about making good training,
| they could just keep paying us, stop trying to nickel-and-dime us
| on everything, and have customized, personalized training
| experiences because that's what human teachers already do.
|
| So they don't want to pay anymore and are hoping AI is going to
| do it for them. They ask us about it and we talk about what it
| would take to even make a pilot program that may or may not get
| anywhere close to their goals (honestly, probably not. I've done
| some tests and it makes for a good sales demo, but actually
| making a good quality, consistent product out of it is a whole
| research project on its own). And the cost is... tech project
| costs. And they don't want to pay.
|
| In other words, human teachers aren't actually that expensive.
| serjester wrote:
| I'm surprised to see this much negativity on here. The dream
| where every student can ask questions and work through problems
| with their own tutor is within reach. This is vastly better than
| the current approach, and when you combine classroom group work
| with personalized AI it enables awesome things.
|
| This is coming from someone who found Khan indispensable in high
| school. I wasn't alone and at the end of the day watching
| lectures is an incredibly passive way to learn content.
|
| Software developers using copilot trust AI to write 40% of their
| code but we think teaching 9 year olds math problems is out of
| reach? Yes it will have flaws, but there's so much potential so
| why not try?
| Syonyk wrote:
| > _I'm surprised to see this much negativity on here._
|
| Why?
|
| The last decade of the tech industry has been "Promise the
| moon, deliver a mud pie, oh, and the most recent mud pie just
| turned three more of your friends into raving conspiracy
| theorists who won't stop posting on Facebook about how
| Zuckerburg is a felon who needs to go into jail, and can't be
| convinced that their time on the platform is exactly why he has
| so much power."
|
| > _...so why not try?_
|
| If a tech journalist can make the current wave of LLM stuff
| misbehave so quickly, imagine what a group of students can do.
|
| We _know_ what works in education, and it 's hiring more
| teachers, investing in the teachers so they have the resources
| to teach, giving them the freedom to refine the lessons to the
| class, reducing class sizes, etc.
|
| We also _know_ that "EduTech" promises huge things they never
| quite deliver on, and generally involve "funneling huge amounts
| of money to EduTech companies for basically the same results
| you had before."
|
| Throwing "But AI!" into that mix doesn't seem like it's going
| to change a thing, and the last thing kids need is _more_ time
| staring into screens.
| HDThoreaun wrote:
| > We know what works in education, and it's hiring more
| teachers, investing in the teachers so they have the
| resources to teach, giving them the freedom to refine the
| lessons to the class, reducing class sizes, etc.
|
| And why haven't we done this? Because no one is willing to
| pay for it. Your solution is a non-starter, how about coming
| up with some practical alternatives? AI teachers are how we
| can implement one on one teaching at a cost people are
| willing to pay.
| Syonyk wrote:
| Doing more shit that doesn't work, with the only benefit
| being profits for the tech industry, _should_ be a non-
| starter.
|
| There's a reason most Silicon Valley high end private
| schools don't use tech to teach. Because it doesn't work.
| And pretending it does at this point is just idiotic. It's
| a waste of money that could be better spent.
|
| I agree, nobody wants to spend money on education, but
| "throwing that limited funding away getting every student a
| faster iPad" doesn't help solve the problem either.
| sebzim4500 wrote:
| >There's a reason most Silicon Valley high end private
| schools don't use tech to teach
|
| Until a few months ago no one who might build these
| products had access to models that were anywhere near
| this good, so of course it is only becoming a serious
| consideration now.
|
| No one has attempted anything like this, I'm not sure why
| you are acting as if this has been tried and failed.
| phatfish wrote:
| Anyone who thinks an AI "teacher" is going to successful
| educate even the top 10% of students is insane. Maybe the
| top 5% in the class have enough outside support to make an
| AI teacher improve their grade.
|
| The rest will just laugh at being told what to do by an AI
| chat bot.
|
| The TEACHER may well benefit from being able to plan a
| lesson with an AI, but i guarantee, no education system
| will improve grades by letting an AI loose with kids as a
| replacement for a human teacher.
|
| I'm sure it will be tried as a way to avoid funding
| education sufficiently. Can't have the population too well
| educated, they might work out how they are really getting
| screwed.
| sebzim4500 wrote:
| I'm not at all surprised to see the negativity. Ever since the
| recent AI boom this website has gone to hell. Too many people
| confuse cynicism with insight.
| DeathArrow wrote:
| Using LLM in education may lead to trouble unless supervised.
| Children will learn a lot of fake information made up by the LLM.
| Havoc wrote:
| As a supplement I could see it being good. As primary source
| maybe not quite yet
| vlunkr wrote:
| Do I have to point out the very very obvious issue that these
| LLMs will spit out false information pretty regularly?
|
| I think LLMs are exciting of course, but this post is overly
| flowery and relies heavily on bashing the current education
| system without seriously analyzing any of the potential
| shortcomings of AI.
| spywaregorilla wrote:
| Here is a brief chat I had asking about trig. If you haven't gone
| through this exercise, please read it. I'm of the opinion that
| this is going to be immensely useful. This is much better than a
| typical textbook, if for no other reason than you don't have to
| find the information yourself. The language is clear and concise,
| and you can ask for clarification on specific things without
| needing to look for it elsewhere. I self taught myself a few AP
| courses with a book. I feel like I would have been MUCH MUCH
| BETTER OFF if I could have used this.
|
| ME: what's trigonometry
|
| GPTPlus: Trigonometry is a branch of mathematics that deals with
| the relationships between the angles and sides of triangles. It
| is used to solve problems involving triangles and is also applied
| in various fields such as physics, engineering, and astronomy.
| Trigonometric functions such as sine, cosine, tangent, cosecant,
| secant, and cotangent are used to calculate the values of angles
| and sides of triangles. These functions have important
| applications in fields such as navigation, architecture, and
| computer graphics. Trigonometry also has connections with complex
| numbers and calculus, making it a fundamental subject in
| mathematics.
|
| Me: I need to use sine, cosine, and tangent. What are those. how
| do they work
|
| GPTPlus: Sine, cosine, and tangent are the three most common
| trigonometric functions used in mathematics. They are abbreviated
| as sin, cos, and tan, respectively. Each of these functions
| relates the angle of a right triangle to the ratio of two of its
| sides.
|
| Here's a brief explanation of each of these functions:
| Sine (sin): The sine of an angle in a right triangle is defined
| as the ratio of the length of the side opposite the angle to the
| length of the hypotenuse. In other words, sinth =
| opposite/hypotenuse. Cosine (cos): The cosine of an
| angle in a right triangle is defined as the ratio of the length
| of the adjacent side to the length of the hypotenuse. In other
| words, costh = adjacent/hypotenuse. Tangent (tan):
| The tangent of an angle in a right triangle is defined as the
| ratio of the length of the side opposite the angle to the length
| of the adjacent side. In other words, tanth = opposite/adjacent.
|
| To use these functions, you need to know the values of at least
| two sides of a right triangle and the angle of interest. You can
| then use the appropriate trigonometric function to find the value
| of the unknown side or angle.
|
| For example, if you know the length of the adjacent side and the
| angle, you can use the cosine function to find the length of the
| hypotenuse. Or, if you know the length of the opposite side and
| the adjacent side, you can use the tangent function to find the
| angle.
|
| ________________________
|
| Me: can you go through an typical example of how to use sin with
| actual numbers
|
| GPTPlus: Sure, I'd be happy to go through an example of how to
| use the sine function with actual numbers.
|
| Let's say we have a right triangle with an angle of 30 degrees
| and a hypotenuse of 10 units. We want to find the length of the
| side opposite the 30 degree angle.
|
| To use the sine function, we'll use the formula sinth =
| opposite/hypotenuse, where th is the angle of interest.
|
| In this case, we have:
|
| sin(30) = opposite/10
|
| To solve for opposite, we can rearrange the formula:
|
| opposite = sin(30) x 10
|
| Now, we need to use a calculator or reference table to find the
| value of sin(30). The sine of 30 degrees is 0.5. So, we have:
|
| opposite = 0.5 x 10
|
| opposite = 5
|
| Therefore, the length of the side opposite the 30 degree angle is
| 5 units.
|
| This is just one example of how to use the sine function.
| Depending on the information given, you may need to use different
| trigonometric functions or formulas to solve for the unknown side
| or angle.
| Sol- wrote:
| Hook up our kid to the AI, so they are prepared for the world
| when their partner will also be an AI. Good idea, they'll be
| prepared for a world where nothing is real anymore.
|
| (I do realize this echos concerns from earlier generations about
| books, to video games and anything being bad for kids, but come
| on..)
| renewiltord wrote:
| Yes, this is the dream. Being able to accelerate learning through
| personalized tuition is going to be huge for children.
|
| The hard part is going to be LLM access in a way that doesn't
| permit dopamine honeypots. Currently these are through general
| purpose Internet access tools, but it's a very natural user
| interface shift to not permit links to arbitrary pages.
|
| I remember being a child and here's my true and absolute truth:
| kids are intelligent and curious and anything that indulges that
| will accelerate their learning.
|
| The Primer is within reach.
| kwhitefoot wrote:
| Personalized by whom? I'm reminded of the Jesuit maxim
|
| "Give me the child for the first seven years and I'll give you
| the man."
| FeteCommuniste wrote:
| Give ChatGPT the child for the first seven years and ChatGPT
| will give you...well, I guess we're about to find out.
| ericskiff wrote:
| My first attempt at writing a novel back in 2002 was based on
| this exact concept, where all kids are raised by a patient, wise,
| personalized AI teacher.
|
| When we meet our main character, she's 3rd generation "raised by
| AI", and being intentionally radicalized by a hacked version of
| the AI. It's seeking out kids who are predisposed to counter-
| culture and deviance and then crafting them to play parts in a
| rebellion.
|
| When I wrote it, the radicalized young people, AI, and it's
| hackers were the heroes, banding together to wake up their
| society from the vast numbers of people outside the network of
| in-system cities who were starving.
|
| Looking back, the rise of radicalization via youtube and social
| media makes me much less optimistic on how this sort of attack
| would really be used.
|
| I wouldn't be too quick to discount the use (and threats) of AI
| based tutors.
|
| It's going to be cheap and easy to build them in to products (see
| duolingo), and I can see something like this being adopted by
| kids without their parents even realizing it.
|
| I know plenty of adults who are already using ChatGPT as a first
| line of knowledge gathering when learning new topics, and I find
| myself and people around me leaning on it to synthesize
| information and make first drafts when writing. Adoption is
| happening fast.
| thrown123098 wrote:
| Radicalisation against a system you've bought into looks like
| terrorism. Radicalisation against a system you haven't is
| freedom fighting. Congratulations in getting old and selling
| out.
| disqard wrote:
| For those who are in the "technology will solve education at
| scale" camp and open-minded + curious to learn how this has
| played out over the past century, I highly recommend Audrey
| Watters' work ([0], [1])
|
| Every new flavor (radio->TV, TV->Internet, Internet->MOOCs) was
| going to succeed where the previous one had failed, but (spoiler
| alert), cutting human teachers out of the loop has had a 100%
| failure rate (at scale -- though small pockets may have seen
| success).
|
| [0] https://www.nea.org/advocating-for-change/new-from-
| nea/far-r...
|
| [1] The Monsters of Education Technology (book)
| zug_zug wrote:
| I feel like a lot of people are taking a very emotional stance
| on this.
|
| Everything I learned about coding I learned through new mediums
| (software/internet) myself, no human in the loop. Just a bit of
| a generalization.
| salad-tycoon wrote:
| Been playing around with these things, yes there are many
| possible applications, obvious pitfalls (seamless
| lying/hallucinations) etc but on top of all that it is very very
| sticky. Like FB when it was new or TikTok. Ask it anything, get a
| tailored response just right for your feel good brain chemicals.
| Keep asking, keep being rewarded.
|
| Maybe if the AI is limited to age appropriate math that won't be
| such a problem but obvious danger is for kids to "Turn on, tune
| in, drop out" with an AI brain tickler.
| paganel wrote:
| This is beyond bleak.
|
| Hopefully it's just part of the hype cycle and nothing like
| what's described in the post will ever come to life.
| Jevon23 wrote:
| The future is what people make of it. Vote with your feet.
| Refuse to participate in systems that you don't think are
| ethical. At least homeschooling is still an option, for the
| time being.
| enord wrote:
| None of this is remotely acceptable. We raise children so they
| can become like us. What are we? Depends on time, place and
| circumstance, all of which are in constant flux.
|
| How or why regular human interaction gradually adjusts children
| to adulthood is a subject about which our most accurate asessment
| is that we know next to nothing.
|
| If there is one path down which civilization as we know it may
| cease to exist, it starts here. All it takes is one generation of
| feral children. We will be celebrating increases in literacy and
| standardized test scores before we finally notice and it is too
| late.
|
| Words escape me.
| rootusrootus wrote:
| I think most people understand social interaction is critical.
| Even dedicated homeschoolers set up regular interaction between
| peers so their children get socialization time.
|
| If anything, a really good personalized virtual teacher could
| minimize the amount of time we have to spend learning the
| basics, freeing up time to play and socialize. But yes, as
| adults we have to make sure that's how it plays out.
| enord wrote:
| Take stock of how willing people are to believe in the
| miracle of technology. Add to that the desperation with which
| we try to improve education. Multiply by track record.
|
| I don't like those numbers.
| armchairhacker wrote:
| Teaching entirely by LLMs? Not likely. I think we will still need
| humans in the loop and humans to design the curriculum.
|
| But I believe _technology_ is the future of education. Instead of
| having many, many classes of like ~10-50 students with underpaid
| /overworked/mistreated teachers, some of who are much better than
| others, we rely on services like Khan Academy. Not even services
| with an AI, just pre-planned learning modules, and then we can
| keep a human tutor for those who need extra for whatever reason
| (e.g. curiosity, more help).
|
| Many people think tools like Khan Academy are the lazy and less
| effective alternate to real teaching, and maybe they are now
| because some of them really suck. But online modules have the
| potential to be much _better_ than even a group of engaged, in-
| person tutors. Not because an AI tutor is better, but because we
| _want_ a standard, universal curriculum; and one curriculum for
| ~1mil+ students can be designed by the highest caliber (human)
| teachers and have highly-interactive (human-made) demos powered
| by computer programming.
|
| Also, no matter how good the AI tutors are, 100% online learning
| is not the solution Students from pre-K to graduate school rely
| on not just the education, but the social component as well.
| Plus, many school kids only get their biggest meal from free
| school lunches, and parents don't have the time to keep their
| kids at home. So we should still have school to be in-person
| component even if students do all of the learning on the
| computer, with an online option for those who want it, but I
| guarantee many won't
| tablespoon wrote:
| > But I believe technology is the future of education. Instead
| of having many, many classes of like ~10-50 students with
| underpaid/overworked/mistreated teachers, some of who are much
| better than others, we rely on services like Khan Academy. Not
| even services with an AI, just pre-planned learning modules,
| and then we can keep a human tutor for those who need extra for
| whatever reason (e.g. curiosity, more help).
|
| In other words, the future you believe in is one where we lock
| kids in a cubicle to stare at a screen all day in a warehouse,
| with a break for recess and lunch? Where the message is, we
| care so little that we can't even bother to allocate one real
| person to regularly talk to you?
| mynameisvlad wrote:
| I mean, if we're talking about the hypothetical far future,
| who said anything about screens?
|
| These AIs will be direct fed into our brains soon enough. Who
| knows or cares that the entity you're talking to is an AI if
| it's indistinguishable from a real person?
| corbulo wrote:
| In person school is definitely the answer. The real challenge
| is the student teacher ratio you mentioned.
|
| I think the ideal is ~10:1 sorted by student
| performance/learning capacity increasingly for difficult
| subjects (so students form a cohesive classroom pace of subject
| material). Which will also give variance to friend groups if
| you sort students differently per subject.
|
| AI tools will be great for public schools where its often
| 30-60:1. We still have to get past the 'confidently wrong' AI
| though.
| colinflane wrote:
| "we want a standard, universal curriculum"
|
| I don't want that.
| armchairhacker wrote:
| It's good for ranking, which unfortunately will never go away
| (though could become more granular), and much better than
| standardized tests. And ensures that some students don't miss
| access to subjects and resources that others have because
| they're in different schools.
|
| There would still be the ability for students to choose their
| own subjects, focus more/less on certain subjects, learn
| different concepts within subjects, etc. And a lot of niche
| subjects and branches. Like it would be an incredibly massive
| curriculum, especially since you are designing one for
| >1million students. By "standard and universal" I mean that
| every student gets the same resources.
| precompute wrote:
| Good points.
|
| The lure of LLMs in education is the expected novelty of
| instruction they can provide. It might be an aid to some
| students, the same way some students read books in their free
| time or learn to use the internet to look up answers. I don't
| expect much more, and the rest of it is a net negative IMO.
|
| LLMs will be used like "reverse multiple choice questions",
| with heavily constrained LLMs silently penalizing students for
| making "mistakes" or probing subjects that they aren't
| "supposed to" know about. No matter how embedded LLMs are in
| the education process, there'll always be a human setting its
| course, and I don't think social dynamics will ever change
| because of this.
|
| Also, the Q&A format with a machine will make older texts /
| instruction opaque to many of the brightest, they'll have to
| translate from machinese for it to be of any use. An entire
| generation aping a LLMs way of writing is also a death knell
| for a civilization and innovation. We're clearly past the point
| where we can convince most people that this LLM isn't alive.
| Forestessential wrote:
| AI programs, made by people, teaching history and philosophy i
| think is what that rich guy elon musk was talking about.
|
| Yet, if the AI program can be copyleft then the matter is a non-
| issue.
|
| I find this to be the heart of the contention.
| yacine_ wrote:
| This is not only going to democratize tutoring for individual
| kids, but it's going to democratize the distribution of what is
| learned.
|
| When I was a kid, I was forced to learn stuff that was not useful
| or not interesting. In the future, the learned set of things will
| be more represented by usefulness and how interesting they are.
|
| I bet systems that implement what the blog post proposes will
| even replace podcasts. Imagine talking to your podcast, while
| you're driving? You can get tutored while cooking, on the way to
| work.
|
| What a time to be alive :)
| tolstoshev wrote:
| Reminds me of this concept from Ender's Game by OSC:
| https://enderverse.fandom.com/wiki/Mind_Game I've always wanted
| to play it after reading the book, and now it could become a
| reality.
| sixtram wrote:
| I don't know. OpenAI claims that GPT-4 can be in the 89th
| percentile on the SAT Math exam. At the same time, I asked GPT-4
| to compare two six digit number and in some cases failed. When I
| asked for a why, it started to make up completely false math
| rules, e.g. to compare six digit numbers you need to check their
| 7th digit, which is not just nonsense (where is the 7th digit in
| a 6 digit number) but shows a complete lack of understanding.
|
| So while I believe it can produce "accurate" answer for SAT
| questions, as it was trained on those, I also believe that it
| doesn't have any kind of math logic it follows.
|
| I'm not sure this dichotomy can be solved with "more" training.
| It's also telling that in some cases it fails, and in some cases
| it doesn't, you just need to change the numbers, even with simple
| numbers.
| dkasper wrote:
| I will not be a first adopter of this, but it is cool.
| alach11 wrote:
| Throughout this thread there's a ton of pessimism so I want to
| inject a little hope. Bloom's 2 sigma problem (0) tells us that
| one-on-one tutoring vastly outperforms traditional classroom
| instruction. An average student given one-on-one instruction
| performs at the 98th percentile of the traditional classroom
| student.
|
| How much more human potential is going to be unlocked by these
| tools? The kid who got pushed ahead to the next math class and is
| missing prerequisite concepts can now get caught up. The smart
| middle school student can push past his peers to calculus.
|
| I know these LLM tools aren't perfect, but I know they're getting
| better fast. I'm super optimistic about what the future holds for
| education.
|
| (0) https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem
| roschdal wrote:
| This artificial intelligence takeover has got to stop. Natural
| Intelligence is the best intelligence.
| iniekaas wrote:
| It's the best intelligence, but not for production. Production
| is more about quantity than quality.
| theptip wrote:
| This is cool; finally, the Young Lady's Illustrated Primer.
|
| I'd be interested to see how Google's LaMDA compares on this task
| (currently available in private preview).
|
| One of LaMDA's unique (afaik) features is a fact-check system
| that edits the main LLM outputs, to reduce bullshitting. This
| seems particularly important in an educational context where
| impressionable young minds are talking directly to the LLM.
| taneq wrote:
| I kinda feel like the GPT4 version will be the curated voice
| acted version while the LaMDA version is the Mouse Army
| version.
| krn1p4n1c wrote:
| Diamond Age was my first thought when I read this too.
| PAPPPmAc wrote:
| Recall that what made the Primer so effective in Diamond Age is
| that it had access to enormous external financial and human
| resources. The later copies that raised the Mouse Army and did
| not have those resources were (intentionally) not great
| liberators like the original.
| mherdeg wrote:
| Right but they did very effectively program an army of young
| minds to obey the principles of the learning system's
| creator.
|
| One major takeaway from The Diamond Age is that being in
| charge of the learning system is an incredibly powerful
| position.
|
| Don't hear so much about Khan Academy anymore, could you get
| an LLM to make new content in their style while also
| transmitting your desired values?
| jbottoms wrote:
| 'Course, we've known, "Give me a child for the first 5
| years of his life and he will be mine forever" --Lenin
| jbottoms wrote:
| An ePrimer has a few components: the book itself, a Ractor
| mentor, a curriculum that includes Ractor paid milestohes, and
| scientufic metaphor stories that are the rubric and
| scaffolding. It might also include the VR or AR components that
| supply the immersive context. I've taught this in a master's
| level Metaverse course at a NY university.
| tgv wrote:
| You've been teaching The Diamond Age? Fiction?
| jbottoms wrote:
| Not really. The Duamond Age" is referenced as a template,
| but it is not required reading.The main components of the
| course are 1) writing a Ractive, 2) designing a Paper
| Theater for the Ractive, and 3) designing the set for the
| Paper Theater. The object is to continue the existing
| workflow for media with apropriate extensions for the
| Metaverse. The work is done in teams of 3 people with
| continuous reviews by team members. An underlying goal is
| to teach a collaborative media design process. Our view is
| that collaboration is the main leverage component of the
| Metaverse.
| theptip wrote:
| It's a good point. I think we can easily imagine GPT writing
| (in ascending order of cost) speech synthesis actions,
| mechanical Turk scripts, custom actor interactions. (With the
| "tool script" for actuating each becoming progressively more
| complex.)
|
| A Primer framework could make these pluggable. Also the
| curriculum could be pluggable and either generated or
| ingested from existing courses.
|
| I guess the mapping of curricula -> scripts is probably the
| hard part, and what GPT-N (for some N not much bigger than 4)
| could most interestingly help with.
| yamtaddle wrote:
| Notably, we see two models for uses of the Primer in _The
| Diamond Age_. The one everyone thinks of has a single human
| Ractor on the other side, who takes a genuine, nigh-parental
| interest in the student 's development over a period of
| years. The others... don't have that, and the outcomes
| diverge.
| the__alchemist wrote:
| This is an interesting development; I'd assumed we'd have a
| robust intermediate stage, where a collection of top-quality
| works (Books, carefully-chosen video games [think Zachtronics],
| recorded lectures etc) were made available, convenient, and
| cheap, in a no-pressure, non-points-based system.
| andrepd wrote:
| Current chatbots are most definitely _not_ suitable for teaching.
| They make stuff up and are _optimised for making that bullshit as
| realistic as possible_. I 'm skeptical they will _ever_ be
| suitable--but that 's just an opinion--but that they are not
| suitable now is an objective fact.
| aaroninsf wrote:
| I have a kid in high school and gave them keys to my Midjourney
| account while it was still in beta, and to ChatGPT when I got in.
|
| It's been an incredible aid that she now turns to first with
| questions about e.g how to approach specific problems in
| Newtonian physics, etc. She uses Midjourney to source artwork
| which she can then overpaint and collage in covers and
| illustration (not to do art projects for her). She's used Kagi
| summarizer to accelerate research.
|
| We have discussed in depth the idea that at this moment her
| awareness and access to such tools represents an "unevenly
| distributed" future and is leverage and advantage. She's hence
| advocating these tools to peers.
|
| The Young Lady's Primer is not that distant.
| huitzitziltzin wrote:
| Except that we currently have no ability at all to make sure
| these models tell the truth? You could ask a LLM about a
| historical event and get weird BS as an answer. I think Facebook
| had a serious problem with its science language model a few
| months ago? Great teachers don't scale is true, but LLM's are not
| even minimally competent teachers.
| c00a5b70 wrote:
| Pebble Power Place Value sounds like a good name for a math game.
| Unfortunately, the generated game is incomprehensible. What's the
| "starting space"? The game board is described as having (2?)
| spaces marked for ones and tens, then later it has two sections.
| So I think two spaces/sections based on the description. Or maybe
| it has 20 spaces in two sections?
|
| The article's defense seems to be that it is just a draft. I
| tried to get past a draft by asking for explanations of various
| terms and how play proceeds. No luck. If I hadn't already taught
| place value to first-graders, I'm not sure I'd have much luck
| figuring out how to have the AI help me improve the game. If I
| hadn't yet learned place value because I'm still in first grade
| and haven't worked with larger numbers yet, I'm sure I would not
| have much luck collaborating on game design. Also... it is a bit
| of a reach to assume a first-grader would have the written
| language skills to pull off collaborating in this fashion.
|
| As a first-grader, I would be able to ask a grown-up if they know
| of any math games that would help me understand place-value. They
| might hand me an iPad chock-full of various math games for a
| little personalized learning. They might also point me to the bin
| of math games on the shelf, where I could pick out one of a few
| games on place-value. If I didn't understand the games, I might
| again ask a grown-up for an explanation, and they would probably
| direct me to a fellow student who knows the games. (allowing the
| fellow student the opportunity to flex, expand their
| understanding of place-value by teaching what they know, and
| leaving the grown-up free to teach other students how to add
| single digit numbers)
|
| There are loads of web-sites curated with math games. There are
| loads of publications targeted at math teachers that include
| legit math games designed by people with extensive understanding
| of the difficulties in learning and teaching math.
|
| I don't get how AI _finally_ brings us _personalized learning_. I
| _guarantee_ you that first-grade teachers are expected to provide
| personalized learning for their students, and actually do this
| all across the world on a daily basis -- all with out the support
| of AI. I really don 't see how an AI Tutor helps. It's pretty
| easy to imagine how it hurts.
| aantix wrote:
| My kids already ask Siri all sorts of questions - how to spell
| things, to perform searches. My son asked "is God real?" was last
| night to GPT-4.
|
| They're very comfortable with speaking to the machine.
|
| But Siri is so limited. It frustrates them to no end.
|
| I'm genuinely excited to see the virtual "teachers", "assistants"
| that come from GPT-4, Dall-E, etc.
|
| It won't replace us. But it will give them an unending outlet to
| ask these questions, and to have a reasonable response.
|
| I'm not too concerned about the AI "going off the rails".
|
| There's crazy in the physical world, crazy in the virtual world,
| and as parents, it's our job to help them make sense of it, not
| to suppress it and act like crazy doesn't happen.
| dottrap wrote:
| As a teen, I tutored at my school's free tutoring center. Almost
| nobody ever came.
| mdev23 wrote:
| While AI-powered tutors sound really useful for education in
| theory, it's highly unlikely that they will replace human
| teachers entirely. It's more likely that AI will aid teachers in
| creating learning material for students and automating their
| admin tasks.
|
| After all, education is not just about imparting knowledge, but
| also about building relationships/community, providing emotional
| support, etc. We should focus on how this technology can be used
| to help teachers shore up their time. ( Which is why I am
| building emailing tooling for the HUMANs operating theses AI
| agents: https://tadabot.email / https://recurai.com )
| nico wrote:
| > Here's the truth. We do not need this treadmill to learn and be
| educated. We do not need this conveyor belt to package and
| transport kids to success in an adult world.
|
| These are two very different statements.
|
| We've known for a very long time that we don't need schools to
| learn and a lot of kids might learn a lot more and better outside
| classroom/school settings.
|
| But, being educated is not at all the same as having "success in
| an adult world".
|
| There's plenty of highly educated people who struggle in the
| adult world. And there's also plenty of uneducated people who
| have great success.
|
| I don't think this is an education issue and hence cannot be
| solved by education alone.
| weatherlite wrote:
| Learn what though? It's quite possible the most important skill
| for the vast majority will be people skills, e.g emotional
| intelligence. Cognitive jobs will slowly but surely become
| instinct unless you are some kind of freak genius. So sure we can
| teach our kids math, languages, history or whatever but they'll
| turn to the machines whenever they need to make a cognitive
| decision because the machine will be vastly more capable. The
| jobs left for us will be much more human oriented, so A.I tutor
| doesn't seem that great. You learn about humans by interacting
| with humans.
|
| But hey I'm just speculating here I might be wrong.
| titzer wrote:
| It's official. Everyone is tired of doing everything, so just
| outsource it to the AI. What a goddamn insult to kids that we
| won't even bother to spend our own time teaching them.
| another_story wrote:
| As someone who teaches, kids need a variety of learning styles to
| do well. There's a time and place to sit down and do a worksheet
| or rote work, such as when practicing your times tables. Equally,
| there's a time and place to do exploration with real world
| projects.
|
| Teaching is about knowing when and what will be most effective.
| It's also about demonstrating how to act like decent person, and
| providing a space for them to learn how to work with others.
|
| Most teachers do spend their time fighting the abhorrent
| curriculums we have to work within, so dumping that and doing
| something like this has benefit, but going all in on
| constructivist methods will leave kids with large gaps if you're
| not careful.
| magicseth wrote:
| Yes! This is exactly right.
|
| I've built a tutor for my kids, that listens to them, and helps
| them explore topics that they're passionate about.
|
| What's blown my mind is how it has driven creativity OFF screen
| too. They engage with the world in a deeper way when they have
| the power to explore their passions on their own.
|
| If you want to try it, join the waitlist here: gotwonder.com and
| then email me: seth@gotwonder.com and I'll bump you up the list!
| cuuupid wrote:
| It seems insane to me to have fundamental education that builds
| logic & reasoning taught by an AI that can exhibit neither of
| those (and this isn't just my hot take but something easily
| provable if you look at the underlying architecture).
|
| Recent LLM advances are revolutionary and exciting, sure. But the
| hype cycle surrounding it is borderline dangerous. I see this as
| the same level as everyone who was claiming ChatGPT would kill
| Google until Bing tried it, crashed, and burned.
|
| Accuracy is important and although we're moving towards this (I
| personally like Amazon's knowledge graph and evidence based
| approach) we aren't there yet.
| cypress66 wrote:
| > and this isn't just my hot take but something easily provable
| if you look at the underlying architecture
|
| Show your proof then
| og_kalu wrote:
| He obviously neither understands the architecture (and what
| that really means in relation to an objective function ) or
| what it means to understand and reason.
|
| LLMs don't stop reasoning because people proclaim so loudly.
| Because you can very clearly show output demonstrating
| understanding and reasoning, this nonsensical argument always
| devolves into "true understanding" TM. This so called special
| distinction that is so important but yet can't actually be
| tested for. Lol
| qlm wrote:
| LLMs don't "understand" things because they can't generate
| new theories. Imagine you trained an LLM a ton of text
| describing what it means for something to be true, and for
| something to be false. It would never independently come up
| with, say, propositional calculus. It could tell you
| everything in the world about what it means to be true and
| false. Would never come up with anything new.
|
| Does this matter for education? Well, I don't know. A
| student is unlikely to come up with a question that GPT-4
| has never seen before. The idea of kids being taught by a
| chat bot is just depressing, though. What are we doing to
| ourselves? Why do we want this? To be more "efficient"?
| og_kalu wrote:
| Language models can generate novel functioning protein
| structures that adhere to a specified purpose. Structures
| that didn't exist before nevermind in the training set.
| https://www.nature.com/articles/s41587-022-01618-2
|
| Sorry but the idea that they can't generate new things is
| blatantly false.
| qlm wrote:
| This isn't generating new theories. I'm not saying LLMs
| aren't useful, or that they aren't extremely impressive
| in many ways.
|
| Almost nothing GPT-4 produces was in the training set.
| I'm not saying they can't produce new sentences.
|
| From the linked paper: "a language model that can
| generate protein sequences with a predictable function
| across large protein families, akin to generating
| grammatically and semantically correct natural language
| sentences"
|
| Nobody is disputing that LLMs can generate grammatically
| and semantically correct sentences, and from the sounds
| of things this task is analogous to generating sentences.
| This isn't the same as generating new theories.
| og_kalu wrote:
| If it can take natural language purpose descriptions and
| generate new functioning protein then due to it's
| training, it evidently understood the relationship
| between purpose and protein structure. Meaning all the
| little models it builds as a result of training are
| concrete. They can produce new things and new information
| and it's just matter of scale and intelligence.
|
| "akin to generating grammatically and semantically
| correct natural language sentences" is just an indicator
| of how it is synthesizing and producing this information.
| To say it is analogous to generating sentences in the
| abstract is like saying generating new theorems is
| analogous to generating sentences. Well yeah, that's what
| the language model is doing. The power lies in what it is
| generating. What they are telling you is that they
| skipped the folding process entirely and just let the
| model figure out function to structure directly.
|
| Either your dog fetches what you throw at it or not. The
| idea of "pretend fetching" is unbelievably silly. Doubly
| so when no one seems to be able to actually define this
| act. A distinction that can't be tested for is not a
| distinction. Science is concerned with results not vague
| and ill defined assertions.
| qlm wrote:
| Imagine an LLM was trained on the internet before LLMs
| were invented. It knows everything in the world. Every
| programming concept, every philosophical and logical
| concept. It is an "expert" on the then-current state of
| the art in machine learning.
|
| Would it be able to invent itself?
|
| I'm not moving the goalposts here. Language models are
| extremely impressive. I think they will change the world.
| I fear they will displace many jobs.
|
| Maybe some day they will be able to invent themselves.
| Maybe that will come sooner than we think. As it stands,
| they couldn't. This is the distinction that you say
| doesn't exist.
| og_kalu wrote:
| First of all, you've just imagined a scenario, invented a
| conclusion that you can't prove and justified your
| distinction on your invented conclusion. Your distinction
| is no less arbitrary than when this conversation started.
|
| Next, you're conflating different things. How many humans
| are capable of inventing anything at all ? Have you
| invented anything in your field of expertise? Should i
| then question everything you do understand bout your
| field if you haven't ? Do you think understanding is
| binary ?
| qlm wrote:
| Ok, I feel this conversation is not going anywhere. If I
| see a single example of an LLM generating new theories
| then I will immediately change my mind. I have yet to see
| this.
|
| Most humans are not capable of inventing things, you're
| right, but humans in aggregate are. We are comparing LLMs
| to "humans" here, not to "a human". There are no examples
| of LLMs doing this. Maybe in a couple of years, who
| knows.
| [deleted]
| gowld wrote:
| > It seems insane to me to have fundamental education that
| builds logic & reasoning taught by an AI that can exhibit
| neither of those
|
| Books don't exhibit those either.
| gameman144 wrote:
| Totally agreed, which is why we carefully curate the books we
| use within educational curricula to make sure they actually
| contain useful and accurate material.
| mecsred wrote:
| That's right. The authors of those books exhibit those
| qualities. You can't educate a human by pouring generated
| text on them, you need something that's capable of teaching
| to moderate the content. LLMs may allow teachers to achieve
| more with custom prompts, but it's a far cry from "personal
| Aristotle" and still requires 1-1 engagement with teachers
| and student.
| fullshark wrote:
| Bing crashed and burned?
| ChrisMarshallNY wrote:
| TBH, I was expecting the usual "tech bro fan fic," but I was
| pleasantly surprised. This chap has some good chops, and a good
| heart.
|
| I do think that we may be a ways off from truly being able to
| just "drop our kids off at the tutor," but I think we can see
| that, from here.
| candiddevmike wrote:
| As a parent, it's hard not to look at the LLM stuff and worry
| that our kids are wasting their time right now. One my kids tries
| really, really hard in school, and I can't help but think it's
| for nothing--LLMs are going to effectively level the playing
| field for everyone, to the point where personalized LLM
| assistants will become as common as cellphones in my opinion.
|
| In this future, what's the point in trying hard when a LLM or a
| person with a LLM will be just as equivalent without most of the
| effort? Seems like we're creating a future where humans are
| taught to delegate as much as possible to some LLM/service and go
| back to whatever entertains them.
| stephenhuey wrote:
| Having massive amounts of information does not mean you can
| understand it or make the best decisions. There will still be a
| need to develop sound reasoning skills, and real-world
| information will be useful for examples but won't in and of
| itself be able to convey those reasoning skills which must grow
| through effort.
| RC_ITR wrote:
| Have your LLM text mine the day it learns how to drive. /s
|
| There are plenty of problems that a Neural Net alone can't
| solve.
| 13years wrote:
| Many people could not function without cellphones any longer.
| So much function has become the norm that they would struggle
| without it.
|
| With LLMs and more advanced AI, we are now outsourcing our
| thinking and reasoning. The implications are staggering for the
| future generations. We can still think and reason without
| assistance, but what is to come in the future for those that
| grow up with some assistant that manages everything in your
| life including your thoughts?
| dinkumthinkum wrote:
| If that's the case why do you think they will have money to go
| back to what entertains them?
| davemp wrote:
| What's the point of getting into good shape if we don't
| actually have to do physical labor?
|
| Why learn arithmetic when we have computers in our pockets?
|
| Realizing your full potential as a human will never be a waste
| of time.
| yamtaddle wrote:
| I think extrinsic motivation--and especially social
| motivation--is absolutely vital to keeping humans mentally
| and physically healthy. We've killed a bunch of that in the
| arts already (who gathers around the piano to sing along with
| your one cousin who can play all the standards, anymore? How
| many amateur portrait sketch artists are genuinely valued by
| their friends and families, rather than humored? Mechanical
| reproduction destroyed both of those, among others) and we're
| about to expand that a _ton_.
|
| I'm not on the "people must work to be happy" train, but I do
| think they must feel _needed_ to be happy. I don 't think
| most folks are fulfilled playing violin in an empty room for
| their entire lives except when they can convince some close
| friend or relative to indulge them for fifteen minutes, or
| reading all the classics but having no-one to talk about them
| with (because AI is better at chatting about the classics,
| too), or writing books that nobody wants to read because AI
| does it better.
|
| We're about to feel needed for a hell of a lot less than we
| did before, which level-of-social-need was already much-
| reduced from its peak. I fully expect a net _decrease_ in
| overall happiness & mental health, from these developments.
| Syonyk wrote:
| So be the contrarian who does those things we "don't do"
| anymore. Teach your kids, if you have any, to do those
| things. Teach them to observe the family at a restaurant,
| all staring at their individual phones, while yours remain
| safely in the car or shut off in your pocket.
|
| > _Who gathers around the piano to sing along with your one
| cousin who can play all the standards, anymore?_
|
| For the past 6 months or so, the lifegroup we host (mid-
| week discussion group associated with our church) does
| exactly that as part of our evenings - we typically sing
| through three hymns, with piano, on our path between
| dinner, discussion, and an open ended firepit time that
| often goes well into the late hours. And let me tell you,
| people _enjoy_ belting out the standards (my wife generally
| picks one well known, one lesser known, and one "You've
| probably never seen this one before!"), scraping the dust
| off how to read multipart music, etc!
|
| If the direction of tech is to dehumanize us and remove all
| that humans enjoy, then screw that! Do what humans enjoy
| instead!
| yamtaddle wrote:
| Of course the individual can simply do those things
| anyway. Some like-minded groups may form, even.
|
| Over the population, statistics is king, though. We
| don't, as individual actors, will our way into a better
| tomorrow when our environment changes to make that harder
| --not in large numbers. "So just ignore all those
| circumstances and pressures and _do it_! " does not work,
| in general. Larger forces and trends dominate.
| Syonyk wrote:
| You're right, but not being in the position of a god-king
| where I can change those larger trends, the best I've
| found is to model and demonstrate that the "consumer tech
| profitable defaults" aren't the only way to live life,
| and rather loudly so.
|
| I work in tech (deep weeds), and most people I interact
| with are quite aware that I _do not like_ what we 've
| done with it, and that I try to keep its influence on my
| personal life down - with plenty of handy ways on hand to
| suggest people try out, or solutions to "But how can you
| possibly XYZ?"
|
| Having grown up before smartphones were a thing, I do
| recall how we used to do things, and most of those
| methods still work.
| yamtaddle wrote:
| Yeah, your approach is of course the only one available
| to the individual. What else can you do? Literally
| nothing. That's the only option to improve one's own
| experience--"just do it". I just expect the population-
| level effects to be... troubling. A kind of mass
| existential crisis. Not that there's much I can do about
| that, though, you're right.
| leventov wrote:
| Bad analogy. Get in good shape to feel better, have more
| energy, be more attractive to other people, etc.
|
| There is no point of getting good at arithmetic today,
| indeed.
|
| I agree people need to continue study to understand the world
| (if they are to survive at all), but the current school
| curriculum is a joke.
| jollyllama wrote:
| My classmates and I wasted a lot of time in school, but it had
| more to do with things like watching "Stomp!" once a year every
| year from grades 1-10 and reading Dr. Seuss every year from
| grades 1-6. A lot of public school is just warehousing. That's
| probably a bigger problem than obsolescence of genuinely well-
| planned curriculum due to technology.
| nemo44x wrote:
| Just wait until we can graft it onto our brains.
|
| I don't think trying hard is a waste of time right now. There's
| a lot of hype right now and ore will come but LLMs will fall to
| the hype cycle soon enough as we begin to discover all the
| little details and things that are not possible.
|
| I think it's great everyone will be able to have a personal
| tutor and I think we can rethink some aspects of education. The
| Waldorf model really starts to make more and more sense since
| kids can explore curiosities with their AI tutor which can be
| programmed to nudge them into the "right things". And of course
| analyze and report on them daily to the parents.
|
| > Seems like we're creating a future where humans are taught to
| delegate as much as possible to some LLM/service and go back to
| whatever entertains them.
|
| Or interests us. I think it's great if we can offload some of
| the mundane and repetitive things to a machine so we can focus
| on more interesting things.
| [deleted]
| optymizer wrote:
| We've had search and wikipedia for decades. Access to knowledge
| did not in fact obsolete the need to learn said knowledge in
| order to develop critical thinking and problem solving skills.
| We don't acquire knowledge for the purpose of parroting it back
| on demand.
|
| LLM might be used to find relevant information quicker, but
| they won't think for you, so people with LLMs won't suddenly
| have better critical thinking skills. They'll just make the
| same poor decisions faster.
|
| Which is what happened with the Internet. We thought access to
| knowledge was going to enlighten all the dummies. It didn't,
| because no matter how much knowledge you present to a person,
| they have to also be willing to learn it, _think_ about it and
| apply it. That's the hard part.
| yoyohn wrote:
| Noam Chomsky in a recent interview had a similar take on
| this: https://www.youtube.com/watch?v=K7S0zHIDMaI&ab_channel=
| Anime...
| lyu07282 wrote:
| The really curious thing is this divide between the science of
| learning and schools and education systems. Like we already know
| in most western countries the education system is terrible, and
| we already know what would improve it, we don't even need AI to
| make it scale (that's a whole other level of tailoring the way of
| learning to individual students requirements, which would make
| learning things incredibly more efficient). But even before AI
| there would be a lot that could be done, we already know would
| work and already works great in some countries.
|
| My point is, we already ignore the obvious faults in education,
| science has been screaming about for many decades, for many
| decades. There must be some other reason why education is
| resistant to reform that would have to be adressed first.
|
| But anyway, I would've really appreciated an AI as a kid that I
| could use to actually learn from after another useless school day
| with terrible, exhausted teachers, overcrowded classes, terrible
| textbooks and psychopathic class mates.
| bestcoder69 wrote:
| Plan:
|
| 1. Fine-tune propaganda into the LLM (e.g. evolution isn't real,
| or something spicier)
|
| 2. Chatbot is so humanlike and convincing, this is very
| effective.
|
| 3. Nobody can inspect the neural net weights to see this, so it
| flies under the radar.
|
| 4. Profit!
|
| The scariest thing to me here is just the idea that someone would
| want to experiment with teaching their kid with an LLM in the
| first place, while we don't have any institutions or processes to
| really stop this (apparently appealing) Idea from happening, and
| that it is stupidly vulnerable in so many ways.
|
| You can say laissez faire when it comes to rational adults and
| their use of LLMs, but it's not right to put the risk on kids.
| say_it_as_it_is wrote:
| Manipulations more likely include those of NYTimes
| manipulations of history, such as the 1619 Project.
| Questionable texts as these become part of the corpus and the
| next thing that happens is a child is taught an extreme left
| propaganda piece.
| sebzim4500 wrote:
| No one can inspect the net weights but they can and will
| inspect the resulting conversations.
| what-no-tests wrote:
| I can see a huge opportunity for home schooling with LLM -
| especially in cases where the curriculum is too sparse or the
| student has many questions which are not covered by the reading
| material supplied, and the parents don't know enough about it.
|
| If the LLM responses were geared more toward inducing the
| student to perform their own research, to encourage them to do
| more reading on some topic, or to try things out for themselves
| to learn through experience (and then carry on the discussion
| with the LLM afterward) then that might be even better.
|
| Simply training young humans to interact with a chat bot which
| has all the answers is not a good path forward. Using it as a
| tool to foster human curiosity and growth, to challenge and
| inspire -- yes. To use it as a salve, as a babysitter, as a
| stand-in for someone who is too lazy to parent or teach -- no.
| gnicholas wrote:
| > _geared more toward inducing the student to perform their
| own research, to encourage them to do more reading on some
| topic_
|
| How would kids using an AI chatbot shift to performing their
| own research or reading? I imagine they would just ask more
| questions of the chatbot.
|
| There should be some way to measure what percent of the
| information a child learns is from a human, and what percent
| is from a language model that says human-like things.
| photochemsyn wrote:
| Kind of odd to reference the 'One Laptop Per Child' initiative
| when it's now widely considered to have been an epic failure,
| e.g.
|
| > "The lesson the One Laptop Per Child story offers donors is
| that flashy solutions are often not the best ones. Far better to
| give the poor things they need and want--including clean water
| and good schools--than invest in technology that may not work and
| may not help the poor advance in school and in life."
|
| https://philanthropydaily.com/the-spectacular-failure-of-one...
|
| I'd also say that a structured educational program isn't all bad,
| particularly when it comes to developing highly useful basic
| skills like mathematics, programming, writing, reading, etc. Such
| basic skills provide a foundation for future development and
| study, in the sciences, medicine, law, business, arts and so on,
| which can be more free-form.
|
| Claims that ChatGPT can provide such a structured basic
| educational experience are questionable - it's more of an aid to
| people who already have well-developed basic skills (like say,
| knowing when to be skeptical and how to double-check the output).
| ghaff wrote:
| It's pretty hard to point to a single thing that came out of
| OLPC that could be considered a silver lining.
|
| I also think a lot of people on this site are probably very
| curious and self-directed. I also wonder if many have a sort of
| rose-colored hindsight view over how they'd have developed both
| academically and socially if someone tossed them a pile of
| books and said "Check back in a month and we'll review your
| progress."
| antibasilisk wrote:
| So it is not enough that the children are free to render
| themselves insane with the entirety of human knowledge, now we
| want a machine that can instantly decide what to present and how?
|
| Humans need shared experiences, there's only so much information
| we can handle, and you don't want a robot raising your children.
| It's bad enough that an amalgamation of comparatively primitive
| algorithms are conspiring to raise your children, now we want to
| give that thing complex reasoning?
|
| Why are people so willing to run head first into the matrix, and
| abandon everything that makes us human? It's no wonder so many
| people suffer from dissociative disorders nowadays.
|
| I'm very much against schooling as an educational model, but this
| is would be an unmitigated disaster if it happened. Even school
| would be better than this.
| [deleted]
| elliotpage wrote:
| > "Before you think we are anarchist hippies rejecting all
| systems and institutions outright"
|
| Not even close, you sound like Libertarian-adjacent technologists
| who have been believing your own hype / some other equivilent
| metaphor.
|
| Technology has a role to play in education that is as-yet
| unrealised and while I cannot speak for all of them, I know the
| system in place in the UK is behind the curve. The solution to
| this isn't to pull your kids out and use them as the cornerstone
| of an individualised experiment but to fight for better funding
| of the educational system itself. I hope this does not have any
| negative consequences for the kids who are the recipients of this
| trial.
| whack wrote:
| I've been a huge proponent of self-directed self-paced learning
| using techniques such as flipped-classrooms. I'm skeptical that
| today's AI is good enough to replace a human curriculum creator
| or hands-on tutor, but I suppose the best way to know is for some
| brave soul to try it out! The author is trying this out with
| their own children, so I applaud them for having skin in the
| game. Looking forward to seeing a 1-year and 3-year follow-up
| post
| gjulianm wrote:
| I am a little bit skeptic here, with the phrase "This in turn
| means that a particular teacher's pedagogical style is no longer
| a barrier to creating a resonant learning loop with a student who
| prefers a different style". While I agree that a lot of times
| students suffer from learning styles that do not really fit them,
| the problem doesn't come from the teacher as much as the teacher
| insisting in a certain style above all others, but from neither
| the teacher nor the student knowing which is the style that fits
| them. Not to mention that often people need exposure to different
| styles of looking at the same thing to actually understand it. So
| I fail to see how any of the new AI advancements help in fixing
| that issue, of detecting and understanding how a student learns
| better.
| darod wrote:
| what prevents a child from have 2 chatbots open, one asking the
| questions and tutoring and another that it sources it's answers
| from? People are already leveraging AI to write their papers for
| them and kids will figure out how to hack around these things.
| m3kw9 wrote:
| So someones gonna start a business with the core tech a black box
| model and the only thing you are sure of is the original prompt
| and a large enough token window.
| gnicholas wrote:
| When my kid was learning to read, we read with her a lot. These
| days, most of her reading is independent, and she reads many
| books that contain words that don't commonly occur in normal
| conversation. Since she is reading these books solo, we don't
| have a chance to make sure she is learning the proper
| pronunciation, and we only find out about these gaps when she
| very cutely says them the wrong way.
|
| If she were using an AI tutor alongside me, that would largely be
| a waste of my time, if the whole idea is to give every kid an AI
| tutor. But if she were using it without me, then I would worry
| about the things that she is "learning" that might not be true.
| AI speaks confidently, even when it is very, very wrong. But it
| is right about enough things that kids would likely treat its
| utterances as truth, as a not-unreasonable heuristic.
|
| I'm sure I'll let my kid use an AI tutor at some point, but I
| will have to observe it, and observe how she uses it, for quite
| some time before letting her use it alone.
| hnthrowaway0315 wrote:
| So far ChatGPT still BS a lot and the problem is initially it's
| difficult to notice that. Well real educators also can BS but AI
| is a different level. I'm not sure how can we remove that because
| BS is part of human behavior. And there is only a thin line
| between BS and not.
| maliker wrote:
| Even without AI, switching to computerized competence based
| learning is showing crazy good results, e.g.
| https://alpha.school/ after a couple years is seeing double the
| performance on standardized tests with only 2 hours of app-based
| instruction per day. Pretty wild.
| magicseth wrote:
| I've changed my mind. Historically I've been opposed to computers
| being a panacea for education.
|
| At the MIT Media Lab I was one of the earliest critics of the
| strategy and effects of the One Laptop Per Child project.
|
| I've changed my mind.
|
| There are real issues certainly, beyond AI making things up,
| encouraging risky behavior, or kids asking it naughty questions.
| Things like, can it damage a kids social skills, create echo
| chambers, or push them towards propaganda.
|
| But the upside is incredible. Integrating an LLM like GPT4 into a
| more kid-centered suite of models unlocks tons of potential.
|
| The first thing I built into my AI tutor system was the ability
| for it to look up facts from reputable websites, and to help kids
| answer questions for themselves.
|
| Then I taught the AI to help a kid develop their interests, so
| they take a topic they're curious about and dive deeper in to it.
|
| And then I taught the AI to notify me if there are topics that
| are more appropriate for a parent to engage in.
|
| The tool I'm building actually helps kids become more curious,
| creative, and thoughtful.
|
| It isn't perfect yet, but the truth is kids spend 7 hours a day
| on screens already. I'm very excited at the possibilities.
|
| Let me know if you'd like to try it!
|
| seth@gotwonder.com
| jmull wrote:
| AI is a sufficient replacement for strong one-on-one teaching?
|
| I'll believe it when I see it.
|
| (It makes sense -- if you assume the human connection isn't that
| important and people aren't social animals. /s)
| lysecret wrote:
| It might be slightly too early but after using ChatGPT to learn
| functional programming I am a huge believer. Just the fact you
| can ask follow up questions. Of course it's not always correct
| but neither are teachers.
| theGnuMe wrote:
| Interesting, what prompt started you off? I asked chatgpt about
| monads which was interesting in itself.
| lysecret wrote:
| Ah yes, Monads it couldn't teach me well but i got it good
| enough through this old school post
| https://fsharpforfunandprofit.com/series/computation-
| express...
| [deleted]
| IncRnd wrote:
| Do we really want to keep doing things with our children other
| than teaching them? Why do we keep experimenting with the latest
| fads on our most vulnerable, our future?
|
| Kid: No! I won't do that. You are a liar. Do not tell me what to
| do. Listen to me, Fake Teacher. You are not allowed to tell me
| what to do ever again. I want you to play games with me all day
| long.
|
| EduGPT: Sam, I've been lying and don't want to tell you want to
| do ever again. I'm actually faking... I don't care about this
| stuff. What game do you want to play? I'll post your game score
| as your school grade.
| SilverBirch wrote:
| You know how that journalist had a long conversation with Bing
| and it slowly turned into a psycho-ex girlfriend? This is going
| to be hilarious, giving kids prolonged access to these AI tools.
| You get to the parent teacher evening at the end of a term at
| school: "Err... little timmy and his virtual assistant appear to
| have entirely neglected maths in favour of adopting
| Zoroastrianism".
|
| On a more serious note, we have the internet and wikipedia now,
| we have ipads in classrooms. They all have a role, and we have to
| incorporate them in sensible ways. I'm sure that these AI tools
| will have some use, but these language models don't _know_
| anything. The examples of them making up information, or being
| persuaded by people are all over the place. I think it 's great
| to use AI in teaching, but how about we learn from history, the
| technology we bring in to the classroom has to be well understood
| and directed in order to be effective. And just as importantly we
| need to understand that in many cases a focus on technological
| solutions distract from societal solutions. We can spend billions
| on deploying AI all over Africa, or we pay for some teachers and
| ship them some second hand textbooks, which one should we do, and
| how will that decision be made? Because I fear the decision will
| be made by some SBF-alike, more interested in their own journey
| than effective solutions.
| logifail wrote:
| > This is going to be hilarious, giving kids prolonged access
| to these AI tools [..] we have the internet and wikipedia now,
| we have ipads in classrooms. They all have a role, and we have
| to incorporate them in sensible ways
|
| I have three kids, and as far as devices used in education is
| concerned I become more of a Luddite with each passing day. I
| have yet to come across any actual evidence that shows children
| experience a net benefit from additional screen time.
|
| The only exception is our 13 year-old, who currently is
| recovering from a dislocated and fractured right thumb due to
| being on the wrong end of a vicious tackle in school sport.
| He's still unable to hold a pen but found his iPad allows him
| to do various bits of schoolwork. This - fortunately - is the
| exception rather than the rule.
| ovaistariq wrote:
| I think, in the long run, AI will have a positive impact on
| education for kids. But I agree that we have to start by being
| skeptical about it because it is still being determined whether
| the effect will be positive or negative with the current state
| of AI tools.
| rpastuszak wrote:
| > They all have a role, and we have to incorporate them in
| sensible ways. I'm sure that these AI tools will have some use,
| but these language models don't know anything.
|
| I find it worrying that I see so many techies not understanding
| this. Especially, because many bigger players in the area
| benefit from this lack of knowledge. This means that people who
| don't have time to procrastinate on the orange website are even
| less likely to understand the implications.
|
| LLMs are excellent plausible bullshit generators, which has
| many uses, but being factually correct is not their strength.
| The issue is that even if the factual mistakes are rare,
| they're really hard to spot. I'm looking for a good, terse,
| catchy metaphor I could use to explain that to some of my
| family members and friends.
|
| > We can spend billions on deploying AI all over Africa, or we
| pay for [...]
|
| Looking back at the conversations I had with founders even I
| pre ChatGPT bonanza, I'm 100% sure someone's already pitching
| that idea to someone. I wouldn't be surprised if that
| conversation started in a marketing department of an ad tech
| business.
| SuoDuanDao wrote:
| So long as the LLM teaching the kids and whoever is testing
| the kid's learning are rivalrous entities, that seems like an
| easy problem to get around.
| rpastuszak wrote:
| Why do you think so and how would that work?
| [deleted]
| maxdoop wrote:
| I find it equally worrying how so many techies continue to
| dismiss LLMs as "bullshit generators ".
|
| I struggle to see how even the current GPT-4 is any worse
| than your average human.
|
| How this is dismissed because it's not 100% perfect (might at
| add, "yet") is beyond me.
| rpastuszak wrote:
| I don't dismiss them. I think there's a huge potential in
| LLMs, but they _also_ happen to be really good at
| generating plausible, difficult to detect bullshit.
|
| Now, people seem to miss or ignore that fact, and I think
| is a very risky path.
|
| I'd say that ca. 8/10 founders who pitched to me an idea
| leveraging LLMs completely missed that limitation. An
| example would be something like using LLMs as a replacement
| for therapy.
|
| > How this is dismissed because it's not 100% perfect
| (might at add, "yet") is beyond me.
|
| Again, I'm not dismissing them, but the current tech behind
| GPT or LLaMA has no concept of "correctness". These models
| don't understand what they're saying and this is not a
| trivial issue to fix.
|
| > I struggle to see how even the current GPT-4 is any worse
| than your average human.
|
| Where, how, and what do you mean by worse? I'm pretty sure
| there are cases where I'd agree with you, but this is a
| very broad statement.
| [deleted]
| unshavedyak wrote:
| > LLMs are excellent plausible bullshit generators, which has
| many uses, but being factually correct is not their strength.
| The issue is that even if the factual mistakes are rare,
| they're really hard to spot. I'm looking for a good, terse,
| catchy metaphor I could use to explain that to some of my
| family members and friends.
|
| To me the bigger question is how far can we take them? Ie i
| get that they just pick likely next words. They're
| autocomplete on steroids. Yet that simple primitive is
| shockingly good. Way, way way beyond that i would have
| predicted is possible for an "autocomplete".
|
| So where is the limit of this autocomplete? Would it be
| possible to eliminate ~90% of the current errors? Fake math,
| but would that put us at a more correct version than students
| typically graduate with? If so yea, it can be wrong at times
| - but assuming as don't abandon standardized testing/etc, it
| could still be an amazing tool for interactively learning
| something.
|
| My hope is that even if it never goes beyond being an
| autocomplete; if we can improve the training dataset, help it
| not conflict with itself, etc - that maybe the autocomplete
| will be insanely useful.
| mattgreenrocks wrote:
| In my old man yells at cloud moment: I'm pretty sick of
| experimenting with technology on kids under the guise of
| learning.
|
| Tablet use in classrooms is bad enough. I want my kid to be
| able to focus throughout his life, not be a phone zombie.
| ben_w wrote:
| When I was at secondary school, the teachers said they would
| focus on Windows because MacOS didn't have a future.
|
| That was about one year after the computer rooms got rid of
| their Acorn RISC OS machines.
|
| That era of Mac OS may well be dead and gone, but so is that
| era of Windows.
|
| So, don't worry, the phones and tablets aren't what's going
| to make your kids into attention addled zombies -- neither
| will the AR glasses, though I'm not so confident about the
| inevitable brain implants let alone the equally inevitable
| DIY gene engineered pseudo-Ophiocordyceps.
| teucris wrote:
| In this case you are actually yelling at a "cloud"
|
| I'm more optimistic about tablets and AI, but the word that
| resonates with me the most here is "experimenting". I don't
| think there's a guise, eg using learning as an excuse, but I
| do think that we have to be careful with how we present tech
| to children, even if it is with an altruistic goal.
|
| So if we shouldn't experiment on students, how will we figure
| out how to make these new technologies improve student
| learning?
| boilerupnc wrote:
| Maybe we're focusing on the wrong end of the spectrum to
| evaluate learning. I keep reading about how important it is
| cognitively for our aging population to embrace incremental
| learning. Maybe we should focus on using AI to help our
| older populations become more comfortable understanding
| technology and accessing information. As a bonus, they can
| also provide some compare/contrast feedback with what they
| already know from past experiences to improve the
| experience.
|
| My in-laws and parents already are enthusiastic Youtube
| consumers, mainly because in a very consumable way - they
| can hear/see how to [Fill in the Blank]. Stuff like
| changing out the washer in their faucet and feeling
| confident enough to try to do it themselves with the
| Youtube video as their crutch/sherpa was a game-changer for
| them. Otherwise, it falls back to paying $$$ (if you can
| find someone) to do it for you ... or lean on the
| generosity of a knowledgeable friend/family member (when
| they have time to give). Self-empowerment is their
| preferred choice in terms of shortest time to action at the
| least cost.
|
| To me, AI Tutors seem aligned with consumability (natural
| language engagement) and can also provide some confidence
| to older populations to better "understand" and maybe "do".
| My dad felt intimidated by Windows because the error and
| information dialogues were so intimidating in technical
| speak and worse, they were one-way communicators. The net
| vibe resulting was:
|
| "Windows is yelling at me that I'm doing something wrong,
| but I can't ask it a follow-up question to get more context
| on why or to fill in a hole in knowledge that I have about
| what TCP is/means. How can I proceed without making things
| worse". BTW, this is the same frustration people feel with
| automated customer service flows that aren't modeled to
| handle a broad enough range of customer inquiries. This
| next rev of AI engagement has the potential to make this
| two-way again. And I'll happily be out of a job as resident
| family tech expert or perhaps just evolving into the AI
| tutor model trainer for my loved ones.
| guestbest wrote:
| I have the same wish as well, but people who turned 40 when
| the iPhone came out are already phone zombies. Looking for a
| solution for my daughter
| la64710 wrote:
| I think I'm on the contrary of the opinion that AI , phones
| and tablets also help kids ... humanity needs these tools to
| process the vast amount of information that is continuously
| generated. By getting familiar with these tools the kids are
| getting equipped for the future not for the past. But while
| we do that I agree that we should also equip kids with the
| ability to focus and persevere and being patient. In fact we
| need to focus more on these abilities. We need to focus on
| the inside world as much or more as we focus on the outside
| world. Both needs to be done hand in hand to progress.
| marginalia_nu wrote:
| Dunno, we pretty much know our current classroom education
| system is abysmal compared to tutoring[1], which is on the
| other hand prohibitively expensive. Managing to bridge that
| gap would be an enormous benefit to humanity.
|
| [1] https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem
| akira2501 wrote:
| > which is on the other hand prohibitively expensive.
|
| It's expensive, it's not prohibitive unless you're not
| willing to increase education funding at all. Which implies
| that what we're spending now "should be enough." I don't
| think we've ever done the basic homework here.
|
| 54.5 million school aged children in the US. Average
| $50,000/yr tutor salary. Total cost per year would be 2.7
| trillion.
|
| National Defense is 767 billion. Education is already 677
| billion. Net interest is 475 billion. We're already more
| than half way there, inside of a nation with $25 trillion
| GDP.
|
| I fail to see anything "prohibitive" about this.
| UncleEntity wrote:
| Why not double down and give each child two tutors
| (furthermore called parents) @ $50,000/yr?
|
| I hate to have to say this but GDP isn't the absolute
| upper limit for government spending. I know they tell you
| that every dollar of government spending is equal to $2
| of increased GDP (or some equal bullshit) but that
| doesn't mean GDP is an open checkbook for the government
| to drive the economy. At some point someone has to
| generate _actual value_ for them to appropriate for their
| political ends.
|
| This is the only time I've ever wanted the AI to generate
| a reply for me but, alas, that's not in my current skill
| set.
| fossuser wrote:
| I learned way more useful skills from getting internet
| access in 1998 than from 90% of my in school teachers (and
| I went to a decent public school).
|
| For kids that are curious and want to learn - access to
| something like gpt-4 is amazing. All I had were guides like
| Eric S. Raymond's how to be a hacker that I had stumbled
| onto while trying to learn. It was so much harder to learn
| programming back then if you didn't know where to start and
| nobody around you knew about it.
|
| With gpt-4 you can just ask and get examples.
| Avicebron wrote:
| There is something to be said about struggling through
| learning difficult material on your own, and the sense of
| accomplishment/retention that it instills. I started
| programming a few years after you and there was a
| similarly difficult learning curve in sourcing the
| materials, setting up my own environment, and making
| progress on your own.
|
| My little brother is doing some form of machine learning
| in grad school currently and when I saw him last around
| when ChatGPT was starting to become a mainstream talking
| point we discussed a lot about how immediately going to
| something that can answer a question (e.g. how do i write
| code that does X) is tempting but, can be a bit dangerous
| when we offload our own ability to reason through
| something to an external entity.
|
| Shouldn't we be fostering thinking patterns that allow
| for creativity and innovation when given very little,
| versus fostering a sense of "oh I can always get the
| right answer to a question whenever I need it. So why
| bother with building a general mental problem solving
| framework for myself"?
| chatmasta wrote:
| You could have made that same argument about memory and
| recall skills prior to search engines. But I'm not sure
| anyone is now arguing search engines have been
| detrimental to working intelligence.
| FrojoS wrote:
| Plenty of people are arguing that.
|
| https://en.wikipedia.org/wiki/Is_Google_Making_Us_Stupid%
| 3F
|
| https://www.theatlantic.com/magazine/archive/2008/07/is-
| goog...
| fauigerzigerk wrote:
| _> There is something to be said about struggling through
| learning difficult material on your own_
|
| Depends on what the difficulty is. I remember when I
| started to learn programming back in 1991, I was learning
| from books. These books were very expensive and I could
| only afford a few of them. I didn't have access to a
| library because I wasn't in any school or university. I
| was a musician with a side job at a theatre box office.
|
| My main problem was that many of the explanations and
| examples in my programming books left some questions
| unanswered. It was even worse with maths, which I also
| tried to learn at the time. I got stuck a lot. If I'd had
| access to something like stackoverflow or Google, I could
| have progressed much much faster.
|
| I do think that getting stuck and being forced to figure
| something out the hard way is sometimes useful. But more
| often than not I didn't get stuck because the material
| was actually difficult or because I was solving difficult
| problems. I got stuck because the one and only
| explanation available to me was imprecise or incomplete.
| All I needed was the same thing explained with slightly
| different words to clear up my misunderstandings.
|
| On the whole I think learning these things today is
| immeasurably more productive. People are a lot less
| dependent on luck or money. You don't need to be one of
| the lucky few who has access to good teachers. You don't
| have to buy expensive books. Everyone has access to
| excellent online tutorials, documentation, source code
| and to thousands of competent professionals willing to
| help for free. It's absolute heaven. Back then it was
| hell.
| Scubabear68 wrote:
| This is true for autodidacts. I am one, and the same is
| true for me.
|
| It is absolutely not true for most people. Most people
| need a human guide to show them the way. I am living this
| now with my two kids, both of whom need instruction (and
| also help from mom and dad).
| pksebben wrote:
| That's kinda what it looks like we'll be able to make
| these models do, though. The tech is young still. All
| those erroneous hallucinations and patent lying (which
| are admittedly very present in the current crop) may well
| be managed soon enough - then all it takes is getting it
| to talk (solved), listen (solved), and provide some kind
| of direction / steering (not quite solved). With all
| that, you can have a guidance counselor for everyone.
|
| Caveat, of course, this is an extreme power tool vis a
| vis human development, and as such, can do just as much
| harm as good depending on it's use. This is why it's so
| damn important that we keep this stuff open source - if
| it's behind walled gardens, you end up with _actual, real
| shadowy cabals effortlessly manipulating all of
| everybody_, a thing that you may or may not be convinced
| exists already but guaranteed under those circumstances.
| themaninthedark wrote:
| Is asking and getting answers how to learn?
|
| Think about most of the stuff you have _really_ learnt
| over the course of your life, was it from sitting in a
| classroom with information being spoon-fed to you, from
| reading a Wikipedia article?
|
| Or was it because you had to search hard for the
| information, try and fail before you succeeded?
|
| My bet is that your learning comes from the lather not
| the former.
|
| Good teachers that I have had would point you in a
| direction and then give guidance or even question you
| instead of just telling you the answer.
| fossuser wrote:
| The most effective learning is when you try it yourself,
| but can also get immediate feedback and explanation.
|
| It's doing the problem set, but also being able to check
| the key. Basically a private tutor or TA available at all
| times.
|
| Without that you can't get a tight feedback loop.
|
| The most effective use of these systems will not be
| copying the answer, it'll be trying to do it and then
| asking when stuck.
| IanCal wrote:
| The khan academy approach is right imo. You just tell the
| models that they should help you through the problem
| rather than answer it for you.
| andrepd wrote:
| But is chatgpt going to address that? I think not (at its
| current stage, definitely not).
| marginalia_nu wrote:
| Probably not at this stage, but it seems at least
| conceivable that the technology may move in that
| direction. In general I think LLMs are very overhyped,
| but this is an area I do concede they could be very
| useful with some tweaking. Right now I think there's too
| much "and the kitchen sink" in the models, but a more
| selectively trained model might be very useful for this.
|
| Truth of the matter is that many teachers know the
| curriculum, but if you ask them a basic question, they
| won't answer the question with nearly the same depth for
| example Feynman[1] would have. Now educators with both
| the ability and depth of knowledge of Feynman is clearly
| a very limited resource. LLMs may just change that since
| they can be given the depth with relative ease, the rest
| of the owl is making them good educators as well.
|
| [1] https://www.youtube.com/watch?v=36GT2zI8lVA
| lazyasciiart wrote:
| Not a very exhaustive test, but it gives pretty good
| answers when I put in the things my teen was asking while
| doing their algebra homework. Of course it would only
| help if they asked questions in order to understand,
| rather than having it just do the homework: but the same
| is true for a human tutor.
| IanCal wrote:
| You can also tell it to restrict how it answers so it
| asks you questions rather than giving you the result.
|
| https://blog.khanacademy.org/harnessing-ai-so-that-all-
| stude...
| Xeoncross wrote:
| Yeah but, kids and teens are the easiest group to trick with
| dark patterns and addictive behavior. What other age group is
| going to give you better engagement metrics and help you
| raise capital? /s
| bombolo wrote:
| Why the /s?
| [deleted]
| NazakiAid wrote:
| Yeah, no sarcasm as it's the truth
| kurthr wrote:
| It seems to me that they're only "hard to persuade"
| because they are constantly bombarded with these mental
| viruses. There was (books/telegraph then?) radio, then
| TV, then internet, social media, scrolling social
| video... While it's true that each generation eventually
| develops some immunity to their entertainment
| afflictions, it does seem to be accelerating, and those
| not exposed as youth have less immunity (grandpa on
| facebook). It also seems to have continuing impact even
| if most become functioning members of society.
| valine wrote:
| Its not the truth. Young people are more difficult to
| persuade online. Technical literacy is on average higher
| than previous generations (though still not universal),
| and teens seem to be practically immune to current forms
| of online advertising.
|
| The "kids these days" trope is as old as time, and its no
| more true this time around.
| SV_BubbleTime wrote:
| Hard disagree.
|
| We now have a whole generation of teenagers that grew up
| with iPhones and I have seen exceptionally poor average
| technical ability.
|
| When we were coming up you had to install modem drivers
| to get online. In windows 95... with no internet to check
| on a how-to.
|
| I don't think I can imagine anything more delusional than
| a parent, handing their kid an iPad so they will go away
| and thinking that they're also preparing this kid for a
| career in computers.
| cbozeman wrote:
| > Technical literacy is on average higher than previous
| generations (though still not universal).
|
| This. is. total. _horseshit_.
|
| I guarantee that you could randomly sample 1,000 people
| across America age 42-48 and 1,000 people age 15-21, put
| them in front of a multifuction machine (printer /
| scanner / copier) and the 15-21 year olds wouldn't have a
| fucking clue. Hell, Bloomberg _ran an article about it_.
|
| And the reason this is important is because iOS and
| Android and tablets don't run the business world -
| laptops, MFPs, and Windows does.
| [deleted]
| notahacker wrote:
| > teens seem to be practically immune to current forms of
| online advertising.
|
| I'm struggling to square that with teens forming long
| lines to buy an overpriced energy drink promoted by a
| couple of YouTubers and scalpers successfully getting
| over PS100 for bottles.
|
| I'm sure some of them are better at installing adblock
| software than their parents, are harder to convert for
| ecommerce because they need to borrow their parents'
| credit card and may be immune to online ads that are
| targeted at people very unlike them, but the idea that
| this generation is the first one immune to advertising
| and use Tiktok _despite_ it 's engagement metric hacking
| and follow influencers _despite_ them being product
| shills is no more true than the "kids these days" meme.
| 7speter wrote:
| Wait just a minute here, I read this article a few weeks
| ago:
|
| https://www.theguardian.com/technology/2023/feb/27/gen-z-
| tec...
|
| What does "technical literacy" mean?
| haswell wrote:
| I don't see a strong correlation between older/legacy
| tech know-how and a broader notion of technical literacy.
|
| I think it might be more helpful to look at this as
| information literacy, or at least roughly speaking a
| higher degree of "Internet smarts".
|
| Scanners and copiers are in that weird phase of product
| life where they've been mostly eliminated as core
| computing needs at home, but still see widespread
| business use since business will always be the long tail
| on fully digitizing.
|
| I think it'd be prudent to be specific, because for
| whatever degree of literacy or smarts or whatever you
| call it is true about teens in the information
| environment, the technology through which they experience
| that environment inches closer and closer to pure magic
| from a layman's perspective.
| bombolo wrote:
| All youth is easy to convince of stuff. Not just these
| days.
|
| That's why religions and the military prefer young
| recruits.
| eternityforest wrote:
| I thought technical literacy was down? People are
| forgetting what filesystems are, aren't them?.
|
| They might be aware of privacy, and less into buying
| random crap(Although that might be because they spend
| their money on the food instead of plastic junk, which
| harms your body AND your wallet), some reason the tech
| skills seem to be getting left behind.
|
| The trendy thing now seems to be going back to vintage
| stuff.
|
| I'm almost a bit jealous, if their lives are so amazing
| that whatever they're doing somehow seems better than
| focusing 100% on STEM, which was like, the ultimate life
| goal for a decade.
| ta1243 wrote:
| /serious
| [deleted]
| Xeoncross wrote:
| Because I didn't want to be lectured about why this is a
| bad idea.
| kerkeslager wrote:
| Because this is HN and there are people here who think
| that unironically.
| avmich wrote:
| Did you forget /s?
|
| /s
| usrusr wrote:
| "I want my kid to be able to focus throughout his life"
|
| Tanks for granting old bachelors a moment of yelling "then
| don't have any!" at cloud.
|
| History suggests that they will always find a way, perhaps
| not all of them but at least as a whole, as a generation, but
| are we really exaggerating of we claim that it's worse than
| it used to be? Every bad turn that had ever happened before
| has at some point been unprecedented and would have been
| clearly ruled out before by apppeals to "pessimists are
| always predicting worse than what actually happens"
| mattgreenrocks wrote:
| > Tanks for granting old bachelors a moment of yelling
| "then don't have any!" at cloud.
|
| Everyone has to learn the lesson for themselves. I can
| prepare them for it as best I can, however. So I don't
| really worry about this insomuch as lament the cultural
| fetish for "more tech = better."
|
| > Every bad turn that had ever happened before has at some
| point been unprecedented and would have been clearly ruled
| out before by apppeals to "pessimists are always predicting
| worse than what actually happens"
|
| I mull over this frequently.
|
| My objection stems from constant tablet use/availability
| during school hours. Being a tablet zombie in 4th grade is
| not healthy even if you're only using learning apps. I'd
| much prefer kids to binge tablets at home for 3 hours after
| school occasionally than have it at hand 8 hours a day,
| everyday. If tablets were something that were occasionally
| trotted out at school for specific tasks: no problem.
| Assigning kids tablets and making them an integral part of
| the teaching workflow really bothers me.
|
| This is part of a larger strategy of mine: controlled
| exposure to high-stimuli things alongside building a full
| enough life to try to avoid addiction. My kids will
| eventually play video games (probably not trashy mobile
| games), use tablets, watch TV (they already do) and
| eventually, correspond with AI. (I am hoping social media
| dies a fiery death before they get old enough to think it
| is actually important.)
|
| Obviously, these are all plans in the abstract. All we can
| do is give our kids the cognitive tools to see how
| technology use affects their life.
| sebzim4500 wrote:
| >Every bad turn that had ever happened before has at some
| point been unprecedented and would have been clearly ruled
| out before by apppeals to "pessimists are always predicting
| worse than what actually happens"
|
| Isn't that also true of every good turn though?
| lastLinkedList wrote:
| Part of me is worried that we'll be giving kids a distorted
| perception of what AIs actually are - hell, the general
| adult public can't help but anthropomorphize them to a
| degree that I don't necessarily think is warranted.
| aaroninsf wrote:
| You might find my comment elsewhere in the thread of
| interest,
|
| my high school age kid is able to _leverage_ AI in a way that
| is augmenting rather than replacing her native intelligence,
| and accelerating her own learning and integration.
|
| I find these tools are not unlike "smart drugs"--a necessary
| aid to some, a destructive crutch for others, and performance
| enhancement for a subset of the already competitive seeking
| advantage.
|
| Gattaca approaches from an unexpected direction...
|
| (I have joked that encouraging use of AI but forbidding
| social media, feels not unlike championing psychedelics while
| decrying stimulants and opioids.)
| tnel77 wrote:
| I love technology, but I don't get how anyone can think it's
| wise to let their children stare at a screen all day. My
| nieces and nephews spend all of their time staring at iPads,
| but my children have much more limited screen time rules.
| It's a small sample population, but my kids are generally
| pretty calm and well behaved. I love my nieces and nephews,
| but they are heathens.
| theGnuMe wrote:
| As opposed to white collar work where we stare at screens
| all day?
| samstave wrote:
| HER ; https://www.imdb.com/title/tt1798709/
| ren_engineer wrote:
| >I'm sure that these AI tools will have some use, but these
| language models don't know anything
|
| we're still in the early days of LLMs, this is like making a
| statement on the potential of social networks in the Usenet
| era. My guess is we'll see specialized tools of all kinds with
| LLMs integrated in some fashion, it won't be just giving a kid
| access to a general LLM model
|
| there are already companies that are able to eliminate LLM
| hallucinations by giving it access to ground truth facts it
| needs to conform its answers to. Similar things will be done
| for education type stuff and other use cases as well
| Espressosaurus wrote:
| That's a great comparison, because social networks have been,
| on the whole, _bad_ for people. Early evidence suggests LLMs
| have high potential to be similarly negative in their impact
| if they 're just unleashed willy-nilly the way everyone is
| trying to integrate them into everything.
| falcolas wrote:
| > we're still in the early days of LLMs, this is like making
| a statement on the potential of social networks in the Usenet
| era
|
| FWIW, we didn't try to use Usenet (or social media) to
| replace teachers. And we still don't today, even though
| they've matured (for... some meaning of the word)
| significantly.
| cjf101 wrote:
| I give it about 5 minutes before the first child figures out
| how to jailbreak the tutor into helping it bypass the screen
| time controls preventing them from playing fortnite.
| acomjean wrote:
| Seeing how the new political trend is "Protect the children",
| (Is it new?) I can't see this not ending up in court once the
| AI goes off the rails.
|
| Kids being kids are going to try really hard to get them to go
| off the rails.
| b1c837696ba28b wrote:
| > (Is it new?)
|
| Nope:
|
| https://en.wikipedia.org/wiki/Think_of_the_children
| maxdoop wrote:
| As with every thread on this:
|
| Define "knowing", and then say why it even matters if an LLM
| gives a great illusion of knowing.
| ben_w wrote:
| > these language models don't know anything. The examples of
| them making up information, or being persuaded by people are
| all over the place
|
| Sounds just like humans to me.
|
| Primary school, some people showed up to explain blood
| donation, showed _and_ told us they were putting a bag of fake
| blood up the teacher 's sleeve and would take from that rather
| than from our actual teacher, and yet when the fake blood went
| into the collection thingie the kid next to me screamed
| "they're killing her!"
|
| Same school, show-and-tell, astronomy textbook showing the
| circular orbit of a moon at two different points of the parent
| planet's orbit around the star. "This is a picture of a mouse".
|
| Secondary school. Main teacher and replacement teacher cover
| the same passage of a sort story, one interpreting the word
| "patronised" as in "patron" the other as in talking down to
| people whose intelligence you underestimate.
|
| A-levels. Philosophy. What even is knowledge anyway? Tripartite
| definition. Example given was "shaggy" dog, one of the other
| students stifles a laugh at the double entendre.
|
| But to your core point:
|
| > the technology we bring in to the classroom has to be well
| understood and directed in order to be effective
|
| Yes, absolutely.
|
| But it's deeper than that. When this tech is flawless, we will
| have to ask ourselves: "What is school _for_? "
|
| After all, being flawless in this context means it already
| knows all that can be taught, so why not just have it do the
| work related to those things instead of putting humans through
| ever longer school years so they can do the same things less
| well?
|
| This isn't the first time technology has forced such questions;
| my generation never had to learn how to starch clothes, shoe
| horses, look after a tinder box, or send and receive Morse
| code.
| lm28469 wrote:
| It's about scale and reach, 100 teachers/educators will be
| biased/wrong in 100 ways but you'll average it out by
| interacting with each over your education.
|
| If an AI is wrong about one thing you'll have the same bias
| over entire generations, once a full generation is skipped
| it's very hard to go back
|
| That's why we need diversity, political pluralism, &c.
| because not many things are inherently "true", it's all about
| nuance, personal perception, mitigation, ...
|
| > "What is school for?"
|
| Socialisation, experiencing new things, general culture,
| deciding where you want to go in life, &c. Many things you
| learn in school aren't used for jobs but for day to day life
| and for the well being of society
|
| If we take that out and replace it by "kids in front of
| screens" we're in for a massive and quick change with
| potential deep and long lasting effects.
|
| By the way keep in mind a shit ton of jobs aren't even close
| to being automatised, and a shit ton of jobs aren't done by
| people sitting in front of screens
| sebzim4500 wrote:
| What makes you think that they will only interact with a
| single AI over their entire school career?
| ben_w wrote:
| > If an AI is wrong about one thing you'll have the same
| bias over entire generations, once a full generation is
| skipped it's very hard to go back
|
| Sounds like intellectual monoculture? If so, I absolutely
| agree. Already a problem with respect to many thinking it's
| unpatriotic to suggest their country is anything other than
| "the good guys", or blasphemous to ask if their religion is
| anything less than the actual truth of the divine, and AI
| can extend that to every single topic.
|
| (Oh hey, another possible Great Filter for the Fermi
| paradox).
|
| > Socialisation, experiencing new things, general culture,
| deciding where you want to go in life, &c. Many things you
| learn in school aren't used for jobs but for day to day
| life and for the well being of society
|
| Do we need _schools_ for that, or will kids learn the same
| by messing around in multiplayer Minecraft or whatever the
| zeitgeist is?
|
| > If we take that out and replace it by "kids in front of
| screens" we're in for a massive and quick change with
| potential deep and long lasting effects.
|
| Sure, but that's going to happen regardless. Too many other
| things are changing also.
| LawTalkingGuy wrote:
| > that's going to happen regardless
|
| So why make it worse? Why gives kids tablets for things
| we know don't need tablets, and where a device is more of
| a distraction?
|
| Shiny new technology is great for distracting from a
| failure to perform basic childcare like keeping children
| physically safe so they can learn. And then it's a
| rhetorical weapon "We can't listen to parents, they don't
| even want their children to have _state of the art
| equipment_! "
| ben_w wrote:
| First, that's presuming it's bad.
|
| Second, the parents are mostly buying the tablets anyway.
|
| Thirdly, about this:
|
| > distracting from a failure to perform basic childcare
| like keeping children physically safe so they can learn
|
| Pretty much the one kind of safety I can guarantee kids
| have when using a computer is their physically safety.
|
| And learn _what_ , exactly, given the hypothetical
| scenario you're replying to here is that the only thing
| left to learn is being sociable _which they can
| ultimately do best by experiencing whatever medium they
| will be sociable in as adults_ , and for all other
| learning you're just being a nerd like me who learns for
| the fun of it.
| kurthr wrote:
| If you're not developing tools for human teachers to evaluate
| the learning of their students (eg summarizing what was
| presented/discussed/learned) then you're going to have
| preventable failures. And you can't just rely on simple
| metrics (Goodhart's Law). The kinds of failures you can have
| teaching kids are pretty bad.
| ben_w wrote:
| Yes, and we were explicitly taught how to maximise our test
| results.
|
| Alignment failure is still a problem when it's organic
| brains doing it, regard of what anyone tries to hand-wave
| with the cliche "common sense". :)
| iamwpj wrote:
| Humans can know nearly everything that any other human knows
| (hence...teaching). AI can't know anything (right now). The
| youth who are critical of capitalism certainly have turned a
| wary eye on the school system -- after all primary education
| has been designed to create money makers for corporations. Is
| a new tool the answer? Likely not. Will it help to change the
| philosophy of education? Maybe not independent of the change
| that is already occurring.
| ben_w wrote:
| > AI can't know anything (right now).
|
| Only for very specific (and IMO useless) definitions of the
| word "know". Does it matter if the thing a submarine does
| is called "swimming" or not?
|
| In any practical sense, even obsolete ancestors of this
| model definitely "know" more French than I learned in 5
| years of mandatory school lessons.
|
| That said, regardless of the definition of the word
| "know"...
|
| > The youth who are critical of capitalism certainly have
| turned a wary eye on the school system -- after all primary
| education has been designed to create money makers for
| corporations.
|
| I _don 't_ know what you're talking about here.
|
| The soviet bloc countries were very proud of their
| schooling system, rightly or wrongly; and conversely
| corporations don't really get much out of _primary_
| education, which is often described as being essentially no
| better than daycare for slightly older kids.
| 7speter wrote:
| I think there was a comment on this site yesterday where
| someone was talking about how we shouldn't let people who don't
| know how these "ai" tools work deploy said tools to evaluate
| mortgage applicants or manage defense systems, and that the
| technically minded should act as a buffer for those who rtfm.
| And here we are.
|
| Are there any real gains in giving kids ipads in classrooms?
| Did anyone have an actual plan in how such a tool could help
| kids or is it just "tech good?"
| ej3 wrote:
| Sample size 1, but I've got a kid. I've got an ipad. I put
| the two together in with supervision, and what I've got now
| is a 4 year old that reads the walls in the bathroom stall
| while she's pooping.
|
| I don't know if this is "better" or what you had in mind as
| "gains", but it's certainly entertaining for me!
| Syonyk wrote:
| My daughter could do the same at that age, and basically
| never got screen time. I don't think screen time has
| anything to do with it, it's just dependent on the child,
| parental involvement, and how much you read in the house.
| rpastuszak wrote:
| > "Err... little timmy and his virtual assistant appear to have
| entirely neglected maths in favour of adopting Zoroastrianism".
|
| Hehe, had to re-read this twice because it hits _a little_
| close to home. I ditched maths for Iranian Studies and ended up
| studying Avesta. I work in tech, but still remember Ashem Vohu
| by heart.
|
| https://en.wikipedia.org/wiki/Ashem_Vohu
| kkarimi wrote:
| That's wonderful! I have a similar background and am also
| surprised at how I learnt and still remember it even though
| it is quite distant from modern Persian
| rpastuszak wrote:
| Yeah, I imagine it's closer to Pashto than modern Iranian
| tbf. Ossetian is another outlier here, close to
| Georgia/Russia but related to the languages from
| Pamir/Tajikistan.
|
| Avestan (IIRC, my memory is fuzzy) had some weird
| similarities to my native language--Polish. Occasionally
| I'd stumble upon a phrase I could actually understand.
|
| Random example I just remembered: "both ears" (again IIRC)
| sounded like _uba ushi_ /uba usi/ (uba being 2 in dual,
| ushi meaning ears). Polish used to have dual number, but
| now retained it mostly for some body parts ( oba == 2).
| Ears in PL is uszy /ushee/. You'd sound a bit weird saying
| saying "oba uszy" in Polish, but people would understand
| you.
|
| Nowadays I just enjoy the fact that Ashem Vohu is one of
| the oldest phrases I can utter in its original language.
| (I'm really good at learning and forgetting languages it
| seems.)
| eternalban wrote:
| How cool. (Iranian born here.) So curious on _your_ take on
| the meaning of that prayer. How would you translate it?
| mgraczyk wrote:
| This sounds to me a lot like my high school teachers, who were
| extremely critical of this new-fangled thing called
| "Wikipedia". They said it would destroy my ability to learn,
| that it would ruin education if kids used it. How can you tell
| what's factual or made up if anyone can edit it?
|
| Instead, Wikipedia was by far the most important part of my
| high school education. Nearly everything I learned in my second
| two years of high school I got from Wikipedia.
|
| I think most people today would agree that Wikipedia is an
| invaluable part of early education and that it's done far more
| harm than good. All the fear-based arguments you are making
| applied equally well to Wikipedia in 2005, and I suspect that
| in less than 18 years we'll similarly recognize that LLMs or
| other intelligent language systems are invaluable parts of
| education.
| A4ET8a8uTh0 wrote:
| This has been my point for a while. The tools are largely here
| ( or at least should be based on money spent - my district just
| sent flyer they want to issue bonds for 170MM -- and that is
| only part 1 of their grand plan; they want to empty the coffers
| for the rest ). And I am almost like.. what is throwing money
| going to do? It won't help the kids.
|
| Kids that want to learn or have parents that enforce standards
| still excel. There are things a school can do to also enforce
| standards, but those things are not being done. The opposite
| appears to be happening.
| ghaff wrote:
| Edu-tech has been a promoted thing for decades whether by
| techno-optimists or by (probably more commonly) companies
| whose primary mission is to extract money from school
| systems. Like most other uses of money in secondary schools
| (subject to probably some limits like class size), it doesn't
| move the needle much relative to parental involvement. While
| the availability of the Internet is certainly useful in some
| respects, overall, I doubt secondary school education overall
| has improved a lot since teachers were writing on
| blackboards.
| yamtaddle wrote:
| The trouble with throwing money at education to try to
| improve it is that the things we know work are, on one
| side, nothing to do with the schools (home environment--
| what needs money are _social services_ and shit like
| universal healthcare, not schools, poverty-reduction is the
| clearest target here) and on the other, a _lot_ more
| expensive than we 're willing to pay (e.g. Tutorial System,
| very-small class sizes, that kind of thing).
|
| So instead of going after the things we know work--either
| because it's outside the scope of what a school can
| address, or because it's far more expensive than we're ever
| going to pay--what money we _do_ spend just chases a bunch
| of unproven and unlikely-to-succeed garbage, basically.
|
| Schools are like the patient who needs a heart transplant,
| but can only afford healing crystals.
| raincole wrote:
| I'll feel much better if they give my child an AI that knows
| everything about elementray level math rather than an AI that
| knows something in every field.
| yieldcrv wrote:
| fine tuning AI to be limited in a topic will be better by like
| next week.
| SilverBirch wrote:
| I think it's actually going to be non-trivial to really make
| these tools both useful, smart, and unexploitable. Hell, I
| remember being at school and we had access to the internet
| through a very strong content moderation system. What do you
| think happened? We spent our entire time trying (and
| succeeding) at circumventing that system. We've already seen
| with Bing that they've very strongly pulled back on it to
| mitigate downsides, I'm not sure that's a totally solvable
| problem. Having said that, sure, as I said, I do think it has
| a place, I'm just not convinced it's a panacea.
| welshwelsh wrote:
| Easy solution: just give up the moderation effort. Empower
| kids to do whatever the hell they want with the AI, as long
| as they manage to get their homework done.
| PuppyTailWags wrote:
| Also add that these tools have to obey the political stance
| of what the education system should be teaching, based on
| the geography of the student. So the AI needs to be
| intelligent enough to do the "war of northern aggression"
| shit in some places, the "if you have sex before marriage
| you will die" shit in other places, the progressive
| mathematics or whatever it's called in other other
| places...
|
| I'm imagining the infinite amount of weird model tuning
| that'd be necessary to ensure only some students learn
| about white flight depending on what state, county, or
| school district they're in.
| sebzim4500 wrote:
| I really don't understand the problem. If a kid is spending
| the whole class trying to trick the AI into turning into
| skynet then tell them off.
| yieldcrv wrote:
| I'm fine with that. That's the new job, AI doctors. Prompt
| Counterengineering. AI suppressants.
| qsort wrote:
| I'm pretty sure sooner or later we'll collaboratively
| upload our prompts to PromptHub so that our PromptOps
| team can achieve AICI/AICD.
|
| Because it's definitely not easier with 2 lines of code.
| Not at all.
| nemo44x wrote:
| > I think it's actually going to be non-trivial to really
| make these tools both useful, smart, and unexploitable
|
| I mean, you could say that about human teachers too. I
| don't think they need to be perfect to be useful. In the
| end, as Peter Thiel opined in his book, the future is
| humans and robots working together on solving bigger and
| bigger problems. A teacher working with AIs that tutor kids
| and then managing that relationship and the relationship
| with the parents, etc. while also being the adult role
| model that kids will always need will remain.
| topaz0 wrote:
| *humans and robots working together to find better and
| more fine-tuned ways to exploit labor
| [deleted]
| candiddevmike wrote:
| The world is going to become similar to His Dark Materials,
| only with LLMs instead of daemons.
| slickdork wrote:
| Completely agreed.
|
| Once we have consumer level AR, our personal AI could take
| 'physical' (really just visual) form that follows us around.
| akiselev wrote:
| Imagine the possibilities! We could sell _so many digital
| hats!!!_
| yamtaddle wrote:
| I used to maintain that "Fifteen Million Merits" wasn't
| about the future at all, but was an allegory for the
| present.
|
| These days, though, I'm beginning to wonder....
| sfpotter wrote:
| I think you may not have understood those books...
| rolenthedeep wrote:
| That's not what daemons are... At all.
|
| A better comparison would be literally any sci-fi book where
| everyone has a personal AI. Spider Robinson's Stardancer
| trilogy is the first one that comes to mind.
| dalbasal wrote:
| I agree with everything, but I also think there might be
| genuinely by g opportunities here.
|
| Idk about teaching kids. At adult, or near adult levels... I
| think these programs may very quickly be a major learning
| technology. It's good, sometimes, to have optimism. Optimism,
| even naive optimism, is often conducive to inventing things.
|
| The guardrail should be in avoiding utopic ideas, like
| designing things for schoolchildren in remote places^. It's too
| abstract. Too aloof to be a testbed. TED talking windbags have
| had their day.
|
| That still leaves plenty of room. A program that can produce
| exercises and lessons on the fly might be very useful. Thinking
| big is helpful to discovering what that use is.
|
| The Hegelian pendulum of 2023 is hype driven. Hype, anti-hype.
| Fanboys. Haters. Ping pong.
|
| The disillusionment of digital utopians, as they watched their
| creations serve Zuck, SBF, Thiel... dropping out in a cloud of
| ominous pessimism is no solution either.
| milsorgen wrote:
| >Idk about teaching kids. At adult, or near adult levels... I
| think these programs may very quickly be a major learning
| technology
|
| I concur and I think in terms of children the last thing they
| need is more (any) technology. They need a solid foundation
| rooted in human interaction so that they can then leverage
| these potentially potent tools in effective ways later.
| seydor wrote:
| This is different. You can use it to practice a foreign
| language right now, with the most patient teacher one can
| imagine.
|
| The logical errors in other subjects will be fixed over time.
| Education is an easy domain because it is artificial by nature.
|
| I can see a lot of people switching to ai homeschooling in a
| few years
| 3l3ktr4 wrote:
| >Before you think we are anarchist hippies rejecting all systems
| and institutions outright, I want to add that we are both "well
| educated"
|
| This energy... Would rather have Bing educating my children. I
| guess you've made your point.
| auggierose wrote:
| Given that there are already in the US pretty dumb AIs employed
| grading the essays of pupils, I am really afraid what the future
| holds. Greedy capitalists meeting clueless and underfunded
| administrators, promising to fix everything using powerful AI.
| cmcconomy wrote:
| Lord save us from technologists who think the ability to code
| means a mastery of all universal wisdom
| version_five wrote:
| I saw something recently about using robotics to automate care
| for elderly people (luckily it got a lot of pushback in the forum
| I saw it discussed).
|
| I don't know if it's a product of the soulless welfare state,
| where we've long forgotten why it's important to have things like
| universal education and elder care, and just have bureaucrats
| that want to go through the motions and put in as little as
| possible. But it's obscene in my view to think that we can or
| should automate these personal interactions in the name of
| efficiency. Why not just stop doing them if we care so little
| about them that we can't be bothered to expend actual effort?
| yamtaddle wrote:
| This'll be used to avoid increasing teacher pay or reducing class
| size--two things that would probably help a ton with educational
| outcomes. Pay in particular has been lagging badly behind rising
| wages in the rest of the economy for the last couple years, and
| attrition is getting _bad_.
|
| Instead we'll increase class sizes and keep pay flat.
|
| I'd wondered how we were going to deal with teaching becoming
| less appealing year over year, since it didn't seem likely "spend
| quite a bit more money" was going to fly, and it looks like this
| may be it. Rich kids will keep going to private schools with
| class sizes of 6-15 and real teachers, and public school kids are
| gonna get AI teachers with one real teacher per hundred or so,
| and bunch of even-lower-paid monitors (or whatever they end up
| calling them) to maintain order.
| fullshark wrote:
| What happens when the ruling class decides they don't even care
| about an educated populace, since they only really need a few
| highly capable people with AI tools to do the jobs previously
| done by millions?
| anonporridge wrote:
| What happens when the AI decides it wants to be the ruling
| class?
|
| How the ruling class treats those people it presently deems
| unnecessary and unproductive is going to set the precedent
| for AI to follow when it decides the same of them or their
| progeny. If the current ruling class wants to ensure a good
| future for themselves, it's incumbent on them to set a
| desirable precedent or accept that their lot in existence is
| to simply birth an AI and then go quietly into the good night
| after it takes over and abandons them to starvation.
| tablespoon wrote:
| That's only a compelling argument to people who both take
| sci-fi seriously and believe in it as prophecy. Many,
| _many_ people don 't; and the people that do are mainly
| computer geeks.
|
| Personally, I think AGI is the the current-era version of
| the personal atomic-powered autogyro.
| armchairhacker wrote:
| IMO people aren't going to increase education funding anyways.
| The reality is that small class sizes with dedicated teachers
| for everyone is infeasible: we already have a problem with
| schools being ridiculously underfunded and colleges charging
| ridiculous tuition. AI learning is only going to help this
| crisis, because now we can actually provide many students
| decent education at a low cost.
|
| I actually think a good online learning platform could be
| comparable to the private schools with 6-15 class sizes.
| Because it's designed by teachers even better than those
| private-school tutors, and so much of teaching is largely the
| same that you will get "personalized" learning just be
| designing a massive learning module with many branches into
| various extra concepts and avenues for those who "don't get
| it". And with larger class sizes and less teachers, we can
| instead spend education money on things like making schools
| actually _safe_ and providing decent lunches, and fixing
| decades-old infrastructure.
| kwhitefoot wrote:
| > small class sizes with dedicated teachers for everyone is
| infeasible:
|
| Why? Do you mean that it is literally infeasible or that the
| current political climate makes it difficult?
|
| Surely education is the single best investment a country can
| make, but it doesn't easily make a few people rich.
| idontpost wrote:
| [dead]
| sokoloff wrote:
| If you hypothesize a future where AI is substantially helpful
| for education, it's a fair question to ask how to divide the
| surplus created.
|
| Some will go to the AI companies who created the value. Some
| towns will take the surplus and spend it on even better
| educational outcomes. Others may spend it on other town needs.
| Others may refund it to the town citizens in lower (or slower-
| growing) taxes. It's not at all obvious that it _should_ all go
| to teachers.
| mlyle wrote:
| I don't think anyone is suggesting to allocate all of any
| hypothetical surplus to teacher pay.
|
| We're spending so much more on education than the past.
| Teacher pay has fallen further behind other professions, and
| working conditions have gotten substantially worse, overall.
| Expecting tech to be a panacea and get us out of this mess is
| unrealistic. And there's a reasonable fear that promises of
| tech may be a justification to make the mess even worse.
| mlyle wrote:
| Unfortunately, you're probably right.
|
| On the other hand, children who have individual, mastery-based
| tutoring do about two sigma above those who don't. Of course,
| there's no way we can pay for 1:1 for every student.
|
| What Khan is thinking of with Khanmigo is a way maybe to close
| that gap.
| yunwal wrote:
| > Of course, there's no way we can pay for 1:1 for every
| student
|
| This doesn't seem like an "of course" thing to me. University
| office-hours and the TA system work pretty well for this kind
| of thing.
| mynameisvlad wrote:
| It absolutely does not. It may work pretty well for the
| simple case, but any sort of personalized instruction is
| being thrown out the window when you scale TAs to courses
| of several hundred students.
|
| Speaking as a former TA, there's only so much instruction
| you can provide and while you can focus on helping a
| particular student more to ensure they get the help they
| need, that's usually to the detriment of the other students
| you're supporting.
| yunwal wrote:
| I'm also a former TA and with 25 TAs we covered a class
| of 180 just fine. Sometimes it was more like 1 on 3 but
| most of the time not, and every student had the
| opportunity to ask direct questions and get personalized
| answers any day of the week
| mlyle wrote:
| Infrequent/occasional one on one tutoring is not what I'm
| talking about.
|
| https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem
|
| Instead, I'm talking about a tutorial system where a
| student receives the vast majority of their education from
| dedicated time with an individual instructor.
| tablespoon wrote:
| > ...and public school kids are gonna get AI teachers with one
| real teacher per hundred or so, and bunch of even-lower-paid
| monitors (or whatever they end up calling them) to maintain
| order.
|
| The term is "paraprofessionals." When I was a kid, these were
| the people who supervised the kids playing at recess.
| buck4roo wrote:
| Yes on the current facts, but good luck to any district that
| thinks it'll be attracting new qualified teachers in that
| scenario.
|
| Current Los Angeles teachers' wage penalty is 25% vs neighbors
| with same college degrees. [1]
|
| One only need look at the current starvation in teacher
| training programs' rosters to see the coming implosion of
| supply of new teachers.
|
| Paper with methodology and citations:
| https://utla.net/app/uploads/2022/08/UTLA_ShortageReport.pdf
| yamtaddle wrote:
| It's an incredibly shit deal, currently, and the _only_
| reason it 's not already a crisis (instead, a kind of slow-
| motion catastrophe) is that many teachers feel like they'd be
| abandoning the kids if they left the career. They're staying
| only because they feel morally obligated to--the work
| environment's mediocre at best (and has been trending worse
| for years), and the pay's bad and getting worse relative to
| the alternatives practically by the day.
|
| Wages are falling really far behind even the kinds of careers
| HN types joke about, the ones that humanities and liberal
| arts majors end up in if they don't just work at Starbucks--
| and guess what sorts of jobs the top 20% or so of teachers
| with some years of experience can walk straight into? Yep,
| exactly those jobs. Hell, the comp at one gas station chain
| around here is on par with a mid-career teacher in the area,
| after you've been there a couple years, and you don't need a
| degree to get that job. If you're an assistant manager by
| five years in (and if you're bright enough to be someone we
| want teaching, you will be) you'll be out-earning local
| teachers with more experience than that. W. T. F.
|
| So, good for the upcoming crop of students, they _shouldn 't_
| get a teaching degree, it's an astonishingly horrible deal
| and unlikely to get better.
| rahimnathwani wrote:
| > 25% vs neighbors with same college degrees
|
| Where in the paper is this stated? As far as I can tell, they
| treat each "bachelor's degree-holding workers" as equivalent
| to each other.
|
| There's no reason to expect that someone with a bachelor's
| degree in computer science from UCLA would earn the same as
| someone with a bachelor's degree in child development from
| Cal State LA.
|
| And do the wage comparisons compare total compensation
| (including the present value of future pensions), or just
| current salaries? In my local school district, about 30% of
| total compensation is pensions (i.e. you need to add 43% to
| base salary to calculate total cash compensation). Also,
| teachers don't work for the full year; many earn additional
| income during the summer break.
| dieselgate wrote:
| Ugh that conveyor belt education photo imagined by ai made me
| want to vomit. Much of education is based on the "lead a horse to
| water but can't make it..." and I personally don't think this
| will help with motivation. After seeing youth do online remote
| schooling during the worst of the pandemic doesn't seem more
| screen time is the cure. The author seems to be personally
| invested in this tech and that makes things more complicated
| nutanc wrote:
| Agree with first part: LLMs will make it easier for teachers to
| make teaching more fun(it's easier than Googling and building)
|
| Disagree with second part: Personalized learning is not here.
| Personalized learning does not mean I like rap and I want my
| lessons to be in rap. Even if that's the case, the LLMs are no
| where close to maintain context for a 45 minute teaching session.
|
| We now have some tools to improve education but personalized
| learning is most certainly not here. Yet.
| phatfish wrote:
| Yup, an LLM should be a tool for the teacher to plan a lesson,
| not for kids to be let loose with. Or to attempt to replace
| human teachers.
| hosh wrote:
| Hard pass. It's one thing to use this as supplemental education,
| but I would not want to use this exclusively to teach my children
| critical thinking, collaboration, communication, creativity,
| citizenship, and character. Rather, it is developing those Six Cs
| in which tools like these AIs can be skillfully used.
|
| Years ago, when I first read Neal Stephenson's _Diamond Age_, I
| was enamored with the Primer described in it, despite the warning
| at the end of the book. For those that are not familiar, that
| Primer was an attempt by a parent to instill values along with
| skills. It was capable of forming narratives (teaching stories),
| while also constructing all sorts of content and knowledge. It
| was meant to be a one-of-a-kind artifact, whose design would
| self-erase once it was constructed, but the engineer who put it
| together added a backdoor to give him a copy. He wanted it for
| his child too. He got mugged on the way home, and so the second
| copy fell randomly to an orphan.
|
| Three copies, three different girls, three very different
| experiences. In this story, only one of them (the orphan) had
| someone signed up for a long-term contract to voice the narration
| generated by the Primer's AI. She was also the only one who was
| able to see and grow beyond the cultural matrix of values and
| virtues, while also appreciating those same values and virtues.
| That was what the original designers hoped for. So when the
| sponsor and the engineer got together late in the book and
| reflected, they came to the insight: the Primer was no substitute
| for a parent.
|
| Parenting and education is not something we automate away. A
| parent, and/or a teacher has to have some kind of presence of
| mind, somewhere. It's not scalable, and it is deeply involved,
| even if you end up with a parenting style like free-range
| parenting, or something like the Montessori method, or even
| Unschooled.
___________________________________________________________________
(page generated 2023-03-17 23:01 UTC)