Ask HN: Any insider takes on Yann LeCun's push against current architectures?

Okay I think I qualify. I'll bite.

LeCun's argument is this:

1) You can't learn an accurate world model just from text.

2) Multimodal learning (vision, language, etc) and interaction with the environment is crucial for true learning.

He and people like Hinton and Bengio have been saying for a while that there are tasks that mice can understand that an AI can't. And that even have mouse-level intelligence will be a breakthrough, but we cannot achieve that through language learning alone.

A simple example from "How Large Are Lions? Inducing Distributions over Quantitative Attributes" (https://arxiv.org/abs/1906.01327) is this: Learning the size of objects using pure text analysis requires significant gymnastics, while vision demonstrates physical size more easily. To determine the size of a lion you'll need to read thousands of sentences about lions, or you could look at two or three pictures.

LeCun isn't saying that LLMs aren't useful. He's just concerned with bigger problems, like AGI, which he believes cannot be solved purely through linguistic analysis.

The energy minimization architecture is more about joint multimodal learning.

(Energy minimization is a very old idea. LeCun has been on about it for a while and it's less controversial these days. Back when everyone tried to have a probabilistic interpretation of neural models, it was expensive to compute the normalization term / partition function. Energy minimization basically said: Set up a sensible loss and minimize it.)

I don't get it.

1) Yes it's true, learning from text is very hard. But LLMs are multimodal now.

2) That "size of a lion" paper is from 2019, which is a geological era from now. The SOTA was GPT2 which was barely able to spit out coherent text.

3) Have you tried asking a mouse to play chess or reason its way through some physics problem or to write some code? I'm really curious in which benchmark are mice surpassing chatgpt/ grok/ claude etc.

Mice can survive, forage, reproduce. Reproduce a mammal. There is a whole load of capability not available in an LLM.

An LLM is essentially a search over a compressed dataset with a tiny bit of reasoning as emergent behaviour. Because it is a parrot that is why you get "hallucinations". The search failed (like when you get a bad result in Google) or the lossy compression failed or it's reasoning failed.

Obviously there is a lot of stuff the LLM can find in its searches that are reminiscent of the great intelligence of the people writing for its training data.

The magic trick is impressive because when we judge a human what do we do... an exam? an interview? Someone with a perfect memory can fool many people because most people only acquire memory from tacit knowledge. Most people need to live in Paris to become fluent in French. So we see a robot that has a tiny bit of reasoning and a brilliant memory as a brilliant mind. But this is an illusion.

Here is an example:

User: what is the French Revolution?

Agent: The French Revolution was a period of political and societal change in France which began with the Estates General of 1789 and ended with the Coup of 18 Brumaire on 9 November 1799. Many of the revolution's ideas are considered fundamental principles of liberal democracy and its values remain central to modern French political discourse.

Can you spot the trick?

When you talk to ~3 year old children they hallucinate quite a lot. Really almost nonstop when you ask them about almost anything.

I'm not convinced that what LLM's are doing is that far off the beaten path from our own cognition.

Interesting but a bit non-sequitur.

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

> 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.

Coconuts!