Building a real-time AI tutor for 5-year-olds

I think teaching a child to trust an LLM from a formative age is horrifically irresponsible.

If anything, an app should be made where a child learns to correct an LLM's mistakes and learn that it isn't trustworthy.

Actually, better, don't put an LLM in front of children. At all.

EDIT: If a use case is for children who can't afford good education, then use an LLM to make educational materials for children, review them, and make them available for free. After all, the contents are ripped off from human educators anyway.

There is a privacy popup setting for:

  Marketing - These cookies are used to deliver relevant advertisements and track their effectiveness.

  Ello has specific instructions to talk to the child about the learning activities.

There really needs to be more published technical detail on what safety systems you have in this because if trillion dollar companies can't stop AI going off the rails, I feel you're overselling the safety systems you've built.

Reading further it then goes beyond "learning activities" into LLM generated content.

  Some (not all) of Ello’s stories and illustrations have been created with AI technology, and AI allows children to create their own stories and experiences through guided and safe scaffolding.

I'm torn about this.

I primarily think that a a kid who won't pick books is a failure of the family of not noticing their interests.

When i noticed my oldest 3 yr old was obsessed about cars, i bought him a car encyclopedia. He probably could not read most words or did not understand them. But pretty soon he was telling me about car models that i did not even recognize myself.

And as i saw interests, i kept feeding them.

My biggest struggle now is to actually keep books away from them at key times (morning routine, etc) , or keeping bad books (think cynical like My Weird School Daze, etc; or books that openly demean adults or parents) away from them

Start small. Graphical novels, mostly drawings, and continue to buil on that. It can be done. Rome wasn't built on a day.

At some point when they hit 5 yrs old, Grok / OpenAI are great tools to find good series appropriate to their reading level. Before that it can be vibed. Feed the addiction, buy whatever they like.

At some point, you need to watch out for cynical/nasty series. In fact, all of the books we purchase are ranked against peers they have read in the past, or those we know to actively avoid buying due to cynicism, sarcasm, or open disdain towards adults (Wimpy Kid).

At some point around age 9,you will need to decide if violence and some adult themes, are tolerable (Dragon Wing series).

This iterative rocess also works really well for foreign language learning (reinforcing via reading mostly), by leveraging localized RPG video games.

With all that said, notice that I've focused on reading skills.

I don't know how i'd go about replicating this iterative path on other skills like math, mechanical, or electrical engineering learning. That's where I think a busy parent will need to find AI as the solution.

This is one of the most insidious projects I've ever seen and despite the touted credentials of the backers looks to be completely divorced from the realities of how children should be taught.

Full disclosure: I worked on a small project with Ello / Catalin a few years ago.

At the time of writing, the sentiment in this post is that this is a terrible idea, and that kids need human tutors. The latter is 100% true. But also, you might want to know some facts about the state of children's literacy in the US (Ello is a math and reading tutor):

1. We're in crisis. As of 2025, 40% of fourth graders are reading below basic levels [1].

2. There's a massive teacher shortage. 2025 US state data shows ~400k teacher positions either unfilled or underqualified [2] – over 10% of the workforce.

3. Bloom's 2-sigma shows that 1-1 tutoring delivers outcomes at the 90th percentile of classroom teaching. Early research is finding that AI can deliver some of this benefit [3].

4. This can't always be solved by parents: 54% of US adults have a literacy below a 6th-grade level, and 20% are below 5th-grade level [4].

At Ello, I heard stories of children figuring out they were behind at school, and when given the app, they holed themselves up in their room and used it to get themselves caught up. And then they could read! Can you imagine falling behind at this critical juncture, and being stuck illiterate while your friends grow past you? We're currently setting kids up for lives of shame and deprivation.

My take: this really is a life-changing technology. And we need this problem solved. Democracy doesn't function without an educated populace.

[1] https://www.nagb.gov/news-and-events/news-releases/2025/nati...

[2] https://learningpolicyinstitute.org/product/overview-teacher...

[3] https://www.sciencedirect.com/science/article/pii/S2666920X2...

[4] https://www.thenationalliteracyinstitute.com/2024-2025-liter...

Bad idea.

Giving children extended time in front of screens will lead to Idiocracy.

It's a giant No from me.

This is bad and you should feel bad about it. What the actual F? You can't be real man. Yeah, lets just monetize kids and ruin their lifes. What a great idea!

I can't imagine a worse use case for AI. Literally thought the title was a clown

What are your thoughts about children in a Sudbury School model? These are democratic schools where children can do what they like in the day. Mostly they choose to play with other kids, games of imagination, though also doing screen time. One of the basic principles is that children figure out what they want to do and the learning comes along with it; the model views adults wanting children to learn something specific as generally counterproductive though having resources available is okay if it is not coupled with any expectations.

Are your devices likely something that they would have fun with and choose to engage with or is it likely to be ignored unless adults use some kind of persuasion to have them use it? Is it cool with a child using it for a bit and then not using it for a few months and then wandering back to it? How far up into math does it go compared to what an a randomly sampled adult could actually do mathwise? Also for reading, are you using phonics or whole word sighting? For math, to what extent is it screen manipulatives versus manipulations of digits? Also, do you have provision for an older child to start learning this stuff so the basics need not be at a 4 year old presentation level, but the concepts still need to be covered?

In Sudbury schools, the typical age of self-taught reading is 7-9 though it can range from 4 to 12. Useful arithmetic usually seems to happen much earlier than reading though reading tends to get completed by the children on their own while arithmetic does not advance further than the needs of money exchange without special effort. In the long run, Sudbury students have no problem with college level material, including mathematics, but it could be nice to have something that eases the white knuckling if it does not undermine the child's self-directedness.

As many others have said already, training 5 year olds to outsource their brains to a blackbox on the network is a truly horrible idea. They are ruined in their formative years and learn that no thinking is possible without trillion dollar companies.

What makes it worse is that AI is addictive and children naturally gravitate towards the addictive.

I suggest Joe the Camel as a mascot that sold nicotine to teenagers.

I wish I had had this when I was a 5-year-old. Few of my teachers really understood the things I wanted to learn, my peers weren't interested in the nerdy things I was, and my parents certainly didn't have the wealth to provide me with private tutoring. There are a lot of negative comments here, but they are shallow... I'm sure those commenters wouldn't want to live without the access to the Internet, and even a brilliant five-year-old can't use the Internet effectively yet. A smart and curious 5-year-old has endless questions and a properly harnessed LLM has endless patience to provide answers at a level the kind can understand (which usually not even it's parents do).

In fact, this could be one of the most beneficial uses of AI for society yet... private tutors of the level that the mega-rich always had, now for all kids everywhere! This gives me real hope for the future generations of humanity.

https://news.ycombinator.com/item?id=22496163

The reality is, most 5 year olds don’t get access to the resources most of us have had while growing up. People are saying, “kids should have human tutors.” Guys, most people in the world don’t have any tutors! What Ello has built and other forms of AI-based tutoring is going to raise the average level of education and literacy in the world. Especially in developing countries. Let individual parents decide what’s best for their kids.

> A teacher is constantly deciding how to engage a student, whether to say something, draw on the whiteboard, play a game, or change topics entirely.

If it's really true that a teacher's job nowadays is to constantly try to cater to the whims of easily bored and distracted kids, then I pity both the teachers and the kids.

> Effective teaching isn't just about answering a child's question quickly, rather making the right move at the right moment. AI is also going to be an integral part shaping how this generation of kids learn to read and think, tackling this responsibly means getting the design right.

Can you elaborate on what the experience is like for the child? How does this system help them learn? The article focuses on optimizing for interactivity and engagement, but doesn't discuss how this system challenges or facilitates learning and why AI needs to be the solution.

There is absolutely no chance I would allow a 5 year extended exposure to an LLM.

We will look back on this experiment with the same ilk that we have for early screentime for smart phones and tablets as a profound mistake in early childhood development.

Kids learn most from peers and structure up until they are 10. Social queues and behaviors not taught by screens, AI, or your parents.

I strongly feel this should be illegal and the creators of this product should be judged, forbidden from holding any decision making positions in the future, and the families of the children compensated

You are not making the world a better place. You've made the world worse with this project.

I get there are real problems to be solved but so many AI learning tools and apps coming out for parenting/childhood education just don't sit right with me. This included.

Super curious to hear from the parents here: Honestly, at this point isn't not exposing our kids to AI just setting them up to fail in the future? Like not letting them learn to use the internet? I have friends who are actually teaching their kids how to use AI because they don't want them to fall behind

This has fabulous potential if implemented right.

To all the detractors, I would like to point out that your opinion of kids needing a good human teacher is overfit to your experience of having had some of those growing up.

In third world countries like mine, we grow up with absolutely unqualified teachers who were unable to muster anything but a learnt-by-rote understanding of key concepts.

In hindsight these were just desperate adults trying to eek a living for themselves and their family in an impoverished country and resorting to any means by which to do it: gaming the school system or calling in favours to join school faculty. I bear them no ill will. But we as kids were much worse off for it.

I can assure you that no matter what concerns you may have about hallucinations in LLMs, I can bet everything I have that a reasonably modern model (and I'm thinking in the range of gemini-flash, not Fable) in a well designed harness geared towards tutoring would handily and repeatedly outperform every single teacher I had all throughout my schooling.

Don't let a quest for the perfect ruin what is likely already way better than status quo.

Screen time is fundamentally bad for a five year old regardless of the content.

You’re teaching children to behave like machines

a sign of the times. and the times are rotten

Sorry — we had to step away to put our kids to bed, but this post has really blown up! not able respond to every comment right now but just wanted to say one thing: we've been working on this problem for over 5 years now, and our team has witnessed how transformative technology can be when set up correctly to change a child who has fallen behind back up to par, and at times even exceed their peers, in very short periods of time.

Ello 1.0, our reading product that isn’t fully agentic but incorporates extensive use of AI, is already in the homes of tens of thousands of happy families, and every day we continue be be blown away by the messages we receive from our customers for whom Ello has been able to meaningfully impact. We know there's some skepticism on how AI will evolve over time, but we've been witness to how impactful technology can when done right can be. This is why we think it's even more important that we try to get this right, than to simply rule it off the technology because it's AI.

If you want to read up on some reviews from the families using the current version of Ello, you can take a look here: https://www.reviews.io/company-reviews/store/ello

I'm a mom who actually has kids and this thread is insane. 'Just get a tutor'...okay?? Are you paying for it? Because that's not an option for a lot of families. I get that it's more ideal, but the alternative is...nothing? Do you not agree that all kids deserves a chance to read? Are we not seeing the lack of reading proficiency in the majority of American adults nowadays?? Or yall too stuck in your tech bubbles?? There are high school students graduating who cannot do math. This is tech that is actually being used for GOOD here.

AI for kids? Sounds like a bad idea

Oh no. DON'T.

"AI is also going to be an integral part shaping how this generation of kids learn to read and think"

You think they will be even dumber/helpless without gudance from the 'net than Gen Z and A?

Shouldn't this have a "Show HN" in front of it, as per the guidelines?

Curious if this can be combined with AI-generated videos that "maximally drive a targeted brain region" (another post on the front page of HN today).

These poor kids don't stand a chance... to not learn something!

Please, no. The last thing a child need is a screen. Give children books, creative toys, teach them read, enjoy music, do science or any activity always with a human companion and let it be disconnected from the virtual world.

Children do not need screens to learn. I didn't need one when I was a kid, nor endless generations either needed it.

Why are we trying to push everything through an LLM?

This is so cool!

Ignore the haters, AI accelerated education is so obviously a gigantic win for everyone. (And massively levels the playing field.)

Really awesome work! I've been trying to do some of this real time back and forth voice coaching myself and it's no easy feat. Congrats on the progress.

Please don't. Don't deprive children of the interaction with other human beings. 5 year olds don't need tutors. They need play, touch, sense, feel, run, breath, sky, earth.

This is a terrible idea. Screen time hinders the development of fundamental skills, including language and social interaction, especially for children of these ages.

France have already moved to ban screens from places with children under 3. Other countries (including UK, Australia) are also setting strong limits on screen use for kids under 5. This is for a reason.

Products like this are driven by business interests, not good will. Good parenting with screen control is the best way to have a fulfilled and happy child. Protect your children, keep them away from screens while they are under 5 and guide them carefully when you introduce screen time.

What is being taught to 5 year olds? And why would an AI tutor be better than an pre-k learning app

Most students are pretty homogeneous in learning at that stage

It sounds exciting. I think this type of technology will be integrated into all primary education.

Oh fuck off with this bullshit. Not going to slopify my child

This is very sad. Just spend the time in person with the 5 year old, no screens, no AI, nothing impersonal. A 5 year old just wants mommy and daddy in person playing with them. No 5 year old (or any age in that neighborhood) should be exposed to screens.

Gross

The child will be saying "It's not laziness. It's the dog." to her teacher...

the question is, why AI? there are good educational software and games in place that can are fun, engaging and provide meaningful stimulus for children at the age of five.

I didn't realize Ello was so young! One of my kids went from barely a reluctant reader to a proficient reader near the start of your lifetime then, I am deeply grateful we had tried so many things. Massive props.

Pretty interesting. Hopefully this ends up being an affordable solution for without the means for hiring a human tutor.

Dear God no. Keep kids away from AI, and keep AI away from kids. Kids need more human contact, not less.

The more I think about it, the more I want to ban your entire business model

Uniting children with the machine god, what could ever go wrong?

The Ello team nailed it with 2.0, my kids love using this fantastic learning tool and we love being part of the early beta testing program. I know as parents themselves and as early childhood educators the designers have the best intentions in mind when they built this. The friendly interaction between the Ello character and my kids gives them a fun motivation to take on reading challenges beyond their grade level and to fully engage with comprehending the story. I can tell they have already improved with just the few weeks they have been using it. The luddite doomers have this completely wrong as this AI drives a love for reading and reinforces comprehension.

What you're building should be illegal. Educators who use these tools on children should face jail time.

It's hard to overstate the harm of the system you are building. Please understand, there is no way this idea is salvageable or any tweaks or safeguards can make it safe. If you've actually tested this on real children you've already risked extreme harm.

Please, stop.