Earlier quoted context omitted.
So the last scam fell through and they're trying it again?
Yep, but updated for the latest buzzword, and with the humanity removed, as you do in 2026.
2020 -> 2026 ... gunna have to drop the NFTs and put in LLMs
Building a real-time AI tutor for 5-year-olds
291–300 of 460 posts
Re: Building a real-time AI tutor for 5-year-olds
#292Shouldn't this have a "Show HN" in front of it, as per the guidelines?
Re: Building a real-time AI tutor for 5-year-olds
#293a sign of the times. and the times are rotten
Re: Building a real-time AI tutor for 5-year-olds
#294Re: Building a real-time AI tutor for 5-year-olds
#295Earlier quoted context omitted.
I don't think it's quite as simple as that. LLMs do make mistakes but generally with slightly obscure difficult stuff. They're not going to struggle at all with things a 4-9 year old is learning. Also it's not like teachers never make confident mistakes.
> They're not going to struggle at all with things a 4-9 year old is learning. Ask them how many r's are in strawberry. > Also it's not like teachers never make confident mistakes. That's an extraordinary false equivalency that is popular around here. Teachers don't make confident mistakes because the student asked the wrong way. Teachers can be held accountable. Teachers can learn. Teachers can love their students.
> There are 3 letter *"r"*s in "strawberry."
>
> Spelled out: s t r a w b e r r y → the r's are the 3rd, 8th, and 9th letters.
> Teachers don't make confident mistakes because the student asked the wrong way.
I don't see why the mechanism of being wrong matters. If anything it's worse when teachers are reliably wrong independently of how you ask the question.
> Teachers can be held accountable.
lol no. Have you ever tried correcting a teacher?
> Teachers can learn.
Good teachers can learn. The ones that make confident mistakes don't. Anyway no learning is needed for 4-9 year old education.
> Teachers can love their students.
That's just such a weird point to make. It is great that my kids' primary school teachers are super kind and loving. But it's not what they're for, and it's definitely not what AI tutors are for. Nobody is claiming this will replace a hug from a parent.
Re: Building a real-time AI tutor for 5-year-olds
#296Please, 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?
Re: Building a real-time AI tutor for 5-year-olds
#297AI for kids? Sounds like a bad idea
Re: Building a real-time AI tutor for 5-year-olds
#298Screen time is fundamentally bad for a five year old regardless of the content.
Screens are a medium. I don't see how they are inherently bad, although it is probably correct that screens carry the most bad content out of any information medium. But my kid has learned how crayons and instruments are made by watching Mr Rogers, and I simply don't see how he would have learned that via some other medium in the same amount of detail (visual and auditory together). He has seen jazz and classical musicians explain and play their instruments. He has seen how adults interact with each other and respect one another through Mr Rogers and (older) Sesame Street. I've then seen this translate into his real world behaviors. You think that is fundamentally bad?
Re: Building a real-time AI tutor for 5-year-olds
#299Re: Building a real-time AI tutor for 5-year-olds
#300Earlier quoted context omitted.
> Do you actually use these things? I use them every day for SWE. I cannot remember any hallucination from the last 6 months. It pretty much stopped being an issue from the beginning of this year, if you use top paid models. Free models or lower-tier paid models can still hallucinate, though.
I would suggest that your ability to discern when the model is wrong might be the thing that has changed.
This is what it seems to be. I've had to review the LLM output from coworkers who have insisted that the "old" models are terrible but the new ones are very good. They are always discussing the latest models and their tweaks and things.
Their output is just.... not very good. For example, it may not fail tests, but it does so for wrong reasons and will fail under different conditions. Or it checks or guards for things in trivially redundant ways, like doing something like `if (x > 5 && x > 3)` that betray its lack of "knowing" what it's doing. And I can't even get answers from them anymore because they just feed anything I say into the LLM and copy/paste the response.
I'm basically being forced to code with LLMs via review through a person proxy. Or maybe they just have it hooked up to read it directly. It's maddening. It's like having a realistic enough chatbot just shuts people's brains off.