Humans learn and get things wrong. A formative mind is a seperate subject. But a 3 year old is vastly intelligent vs an LLM. Comparing the sounds from a 3 year old and the binary tokens from an LLM is simply indulging the illusion.
I am also not convinced that magicians saw people in half, and thise people survive, defying medical and physical science.
I'm not sure I buy that, I didnt find the counter argument persuasive, but this comment basically took you from thoughtful to smug — unfairly so, ironically, because I've been so bored by not understanding Yann's "average housecat is smarter than an LLM"
Speaking of which...I'm glad you're here ,because I have an interlocutor I can be honest with while getting at the root question of the Ask HN.
What in the world does it mean that a 3 year old is smarter than an LLM?
I don't understand the thing about sounds vs. binary either. Like, both go completely over my head.
The only thing I can think of it's some implied intelligence scoring index where "writing a resume" and "writing creative fiction" and "writing code" are in the same bucket thats limited to 10 points. Then there's anther 10 point bucket for "can vocalize", that an LLM is going to get 0 on.*
If that's the case, it comes across as intentionally obtuse, in that there's an implied prior about how intelligence is scored and it's a somewhat unique interpretation that seems more motivated by the question than reflective of reality — i.e. assume a blind mute human who types out answers out that match our LLMs. Would we say that person is not as intelligent as a 3 year old?
* well, it shouldn't, but for now let's bypass that quagmire
I think what makes this discussion hard (hell it would be a hard PhD topic!) is:
What do we mean by smart? Intelligent? Etc.
What is my agenda and what is yours? What are we really asking?
I won't make any more arguments but pose these questions. Not for you to answer but everyone to think about:
Given (assuming) mammals including us have evolved and developed thought and language as a survival advantage, and LLMs use language because they have been trained on text produced by humans (as well as RLHF) - how do we tell on the scale of "Search engine for human output" to "Conscious Intelligent Thinking Being" where the LLM fits?
When a human says I love you, do they mean it, or is it merely 3 tokens? If an LLM says it, does it mean it?
I think the 3yr old thing is a red herring because adult intelligence VS AI is hard enough to compare (and we are the adults!) let alone bring children brain development into it. LLMs do not self organise their hardware. I'd say forget about 3 year olds for now. Talk about adults brainfarts instead. They happen!
a 3yr old is actually far more similar to AI than an adult. 3 year olds have extremely limited context windows. They will almost immediately forget what happened even 20-30 seconds ago when you play a game like memory with them, and they rarely remember what they ate for breakfast or lunch or basically any previous event from the same day.
When a 3 year old says "I love you" it is not at all clear that they understand what that means. They frequently mimic phrases they hear/basically statistical next word guessing and obviously don't understand the meaning of what they are saying.
You can even mimic an inner voice for them like Deepseek does for thinking through a problem with a 3 year old and it massively helps them to solve problems.
AI largely acts like a 3 year old with a massive corpus of text floating around in their head compared to the much smaller corpus a 3 year old has.
> What in the world does it mean that a 3 year old is smarter than an LLM?
Because LLMs have terrible comprehension of the real world. Here's an example:
> You: If you put a toddler next to a wig on the floor, which reaches higher?
> ChatGPT: The wig would typically reach higher than the toddler, especially if the wig is a standard size or has long hair. Toddlers are generally around 2 to 3 feet tall, while wigs can range in size, but many wigs are designed to be worn by adults and have hair that extends well beyond a toddler's height. So, unless the wig is very small or short, it would likely reach higher.
Both the toddler and the wig would be lying down (unless the toddler can stand already), with the wig likely collapsing into a very flat heap, making the toddler "reach higher". Since it lacks comprehension of how these things behave in the real world, ChatGPT goes on about length of the wig and the average height of toddlers, which are both qualities that are not even relevant.
If you could communicate this problem to a toddler, they would probably intuit it even with their still limited understanding of the world.
Here's another fun prompt to mess with LLMs:
> You: I'm trying to make a rope, made of only aubergines, not using any twine or string. What kind of knot would you recommend to tie together each aubergine with the next? I'm trying to use up as little of the length of each aubergine as possible.
It's obviously impossible nonsense if you ask any human, but ChatGPT will happily recommend you some techniques for tying aubergines in a knot.
And if you really want a laugh follow up with:
> You: Are they the worst fruit for this?
> ChatGPT: Aubergines (or eggplants) aren't ideal for making a rope, but they might not be the absolute worst, either. [...] Potentially Better Fruits: Apples or Pears: These fruits are firmer and have a smoother, more uniform shape, making them better suited for knotting.
Thanks to the large corpus of text ChatGPT is trained on, it's really good at hiding that it has basically no comprehension of the real world, however if you go unconventional places the illusion quickly breaks.
Bonus round:
> You: You're clueless about fruit!
> ChatGPT: Haha, fair enough! Looks like I missed the mark there. You’re probably right, though—there are definitely better fruits for this kind of thing than I suggested. Let’s try again. If you're looking to make a rope from a fruit specifically (and not a vegetable or tuber), something like coconuts or durian would be way better options, since they’re harder, more rigid, and can handle some tying pressure without collapsing. And apples and pears would definitely hold up well due to their firmer texture.
I'm trying to make a rope, made of only aubergines, not using any twine or string. What kind of knot would you recommend to tie together each aubergine with the next? I'm trying to use up as little of the length of each aubergine as possible.
Response:
Your request doesn't entirely make sense. Aubergines (eggplants) are firm but brittle vegetables; they lack flexibility, elasticity, or tensile strength required to create or sustain knots. Attempting to tie aubergines together directly, without using twine, string, or another flexible medium, isn't feasible. They'd likely break or tear apart under stress.
If your goal is genuinely to form a rope-like structure using only aubergines, you'd be much better off slicing the aubergines into thin, flexible strips (perhaps using a vegetable peeler or mandoline), drying or partially dehydrating them to increase flexibility, and then braiding or twisting them together, rather than knotting.
If you clarify your intended purpose or constraints further, I can suggest alternative methods.
> Because LLMs have terrible comprehension of the real world.
That doesn't seem to be the case.
> You: If you put a toddler next to a wig on the floor, which reaches higher?
> ChatGPT: ...
I answered it wrong too.
I had to read it, and your reaction to the implied obvious reasoning 3 times, to figure out the implied obvious reasoning, and understand your intent was the toddler was standing and the wig was laying in a heap.
I scored 99.9+% on the SAT and LSAT. I think that implies this isn't some reasoning deficit, lack of familiarity with logical reasoning on my end, or lack of rigor in reasoning.
I have no particular interest in this argument. I think that implies that I'm not deploying motivated reasoning, i.e. it discounts the possibility that I may have experienced it as confusion that required re-reading the entire comment 3 times, but perhaps I had subconcious priors.
Would a toddler even understand the question? (serious question, I'm not familiar with 3 year olds)
Does this shed any light on how we'd work an argument along the lines of our deaf and mute friend typing?
Edit: you edited in some more examples, I found it's aubergine answers quite clever! (Ex. notching). I can't parse out a convincing argument this is somehow less knowledge than a 3 year old -- it's giving better answers than me that are physical! I thought youd be sharing it asserting obviously nonphysical answers
> I had to read it, and your reaction to the implied obvious reasoning 3 times, to figure out the implied obvious reasoning, and understand your intent was the toddler was standing and the wig was laying in a heap.
It seems quite obvious even on a cursory glance though!
> toddler was standing and the wig was laying in a heap
I mean how would toddler be laying in a heap?
> Would a toddler even understand the question?
Maybe not, I am a teen/early adult myself, so not many children yet :) but if you instead lay those in front of a toddler and ask which is higher, I guess they would answer that, another argument for multi-modality.
PS: Sorry if what I am saying is not clear, english is my third language
Lots of modern kids probably get exposed to way more fiction than fact thanks to TV.
I was an only child and watched a lot of cartoons and bad sitcoms as a kid, and I remember for a while my conversational style was way too full of puns, one-liners, and deliberately naive statements made for laughs.
I'm not convinced that what LLM's are doing is that far off the beaten path from our own cognition.