Live data from Hacker News

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

ello.com

261–270 of 460 posts

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

#261

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…

[dead]

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

#262
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.

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

#263
post #35

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 b…

Thanks for taking time to write this. HN is showing (expected) dismissing attitude towards this idea. That tells me it might work :) ! Folks here are wildly overestimating (or ignoring!) how many adults are qualified to be good teachers and how many of them further have enough incentives (money, time, resources) to do it well. Its a _very_ small number. In my part of the world, "become a teacher" is often a job advis…

Pay your teachers better.

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

#266

Earlier quoted context omitted.

> Most critiques of AI are based on experience with the cheapest AI available a year ago, by midwits You don't even need to use AI at all to have valid critiques of it Plenty of other people are showing its flaws daily by replacing their entire personalities with AI slop Oh it can do some impressive stuff sure. It is still bad for society

> You don't even need to use AI at all to have valid critiques of it You cannot rationally criticize something if you have no up-to-date knowledge about it.

That's like saying you can't know if a stove is hot without putting your hand on it

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

#267

Earlier quoted context omitted.

> 2024 called and wants its talking points back. It's a classic example of the kinds of questions LLMs get wrong. There's plenty of others. Not sure your point here. We can easily find things a 4-9 year old will talk about that an LLM will get wrong, hallucinate, etc. > a child tutored by a good quality state-of-the-art LLM with a good teaching-focused harness could have better learning outcomes than a child without…

> It's a classic example of the kinds of questions LLMs get wrong. There's plenty of others. Not sure your point here. We can easily find things a 4-9 year old will talk about that an LLM will get wrong, hallucinate, etc. My point is that the hallucination rate of modern LLMs, while not zero, is so low that this is no longer an issue in practice. > There's a lot of work being done in 'could'. And it's entirely ignori…

> My point is that the hallucination rate of modern LLMs, while not zero, is so low that this is no longer an issue in practice.

That's just not true. Talk to an LLM about a subject you know deeply. They make up things all the time.

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

#268

Earlier quoted context omitted.

> 2024 called and wants its talking points back. It's a classic example of the kinds of questions LLMs get wrong. There's plenty of others. Not sure your point here. We can easily find things a 4-9 year old will talk about that an LLM will get wrong, hallucinate, etc. > a child tutored by a good quality state-of-the-art LLM with a good teaching-focused harness could have better learning outcomes than a child without…

> It's a classic example of the kinds of questions LLMs get wrong. There's plenty of others. Not sure your point here. We can easily find things a 4-9 year old will talk about that an LLM will get wrong, hallucinate, etc. My point is that the hallucination rate of modern LLMs, while not zero, is so low that this is no longer an issue in practice. > There's a lot of work being done in 'could'. And it's entirely ignori…

> My point is that the hallucination rate of modern LLMs, while not zero, is so low that this is no longer an issue in practice.

Ahahahahahahahahahahahahahahahahaha

Do you actually use these things?

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

#269

Earlier quoted context omitted.

>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. I can understand saying that when you're in middle or high school. But as a 5 year old? This comment has to be a joke?

It wouldn't really surprise me if the average kindergarten teacher (or just adult) had no idea how e.g. an air conditioner or an elevator or one of those emergency flashlights that you can power by shaking or any number of other everyday things works.

Are you asking me to believe that the educational system underserves kindergartners because the average kindergarten teacher can't provide an education on your narrow technical interest?

The responsibilities of the average kindergarten teacher probably include 1) making sure your kids don't swallow glue, and 2) making sure little johnny doesn't throw another tantrum.

Post reply on HN