Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Natural language instructions induce generalization in networks of neurons

nature.com

Post reply on HN
Print view View original

51–60 of 95 posts

Re: Natural language instructions induce generalization in networks of neurons

#51

Post by zer00eyz »

bongodongobob wrote: post #5
zer00eyz wrote: post #3

Earlier quoted context omitted.

I hate the reductive nature of the concept of "latent spaces". A good enough formula for a task isn't a solution for every task. Yes Newtonian mechanics work, but Einstein is a better reflection of reality.

I'm not sure I understand the analogy. The very idea of NNs is that it's not perfect, it is messy and not optimal, but is very generalizable.

>> The very idea of NNs is that it's not perfect, it is messy and not optimal, but is very generalizable.

Newton: Do you need more than that to describe the speed of a thrown baseball on a train? No. DO you you need more than newton to get to the moon? No. Is it going to be accurate at high speed in a large scale system (anything traveling near C)? NO, it fails spectacularly.

NN's are great at simulation, language, weather... But what people using them for weather seem to understand and the ML folks (screaming about AI and AGI) dont is that simulation is not a path to emulation. Lorenz showed that there were limits in weather, that most other disciplines have embraced these limits.

Re: Natural language instructions induce generalization in networks of neurons

#53

Post by photonthug »

somewhereoutth wrote: post #38
lo_zamoyski wrote: post #28

Earlier quoted context omitted.

The distinction between language and "thought" to me is odd. Language and "thought" are the same thing . The mouth sounds or hand scribbles aren't the language, but expressions of it.

You don't need language to catch a ball, but clearly thinking is required to intercept its trajectory correctly. Language is about communication .

There’s an argument that communication which is internal is still communication, and that a language of trajectories required for coordination is still linguistic in a meaningful sense. Most of the ways to differentiate thought from language are probably going to end up splitting hairs. It all comes back to Wittgenstein, and it’s arguable whether the POV is useful, but it’s certainly coherent and defensible.

Re: Natural language instructions induce generalization in networks of neurons

#54

Post by AlecSchueler »

visarga wrote: post #35
worstspotgain wrote: post #15

Birds inspired planes. Later, aerodynamics fed back into ornithology. I've been waiting for LLMs to be evaluated as a model of human thought. Complexity and scale have held neuroscience back. It's nowhere close to building a high-level brain model up from biological primitives. Like ornithology, it could use some feedback. All arguments about AGI aside, a machine was built that writes like a human. Its design is very…

> a machine was built that writes like a human But the real hero here is not the LLM, but the training set. It took ages to collect all the knowledge, ideas and methods we put in books. It cost a lot of human effort to provide the data. Without the data we would have nothing. Without GPT we could use RWKV, Mamba, S4, etc and still get similar results. It's the data not the model. > the intuition that language is cent…

> But the real hero here is not the LLM, but the training set.

And in the case of windmills the hero is the wind. But the mill is still a fantastic achievement.

Re: Natural language instructions induce generalization in networks of neurons

#55

Post by jameshart »

lo_zamoyski wrote: post #28
jameshart wrote: post #14

Earlier quoted context omitted.

Strong Sapir-Whorf (linguistic determinism - language constrains thought) became pretty much seen as a joke by the 1980s. Linguistic relativism (weak Sapir-Whorf - language shapes thought) is still respectable (because, I mean, of course it does). Actually, this research might just as well be evidence for linguistic universalism (Chomsky - language enables thought). In general linguistic philosophers have been coming…

The distinction between language and "thought" to me is odd. Language and "thought" are the same thing . The mouth sounds or hand scribbles aren't the language, but expressions of it.

One issue here is semantics. The things that happen in our brains which we can put into words tend to be the things we categorize as ‘thoughts’. But there are things that happen in our brains which we struggle to connect to language too, and we might call those ‘feelings’ or ‘emotions’ or ‘instincts’ instead. So we’re trying to use language to think about how we think about language and I suspect this might be why that end of neurolinguistics falls off the deep end into philosophy.

Re: Natural language instructions induce generalization in networks of neurons

#56

Post by codethief »

a_gnostic wrote: post #22
jameshart wrote: post #14

Earlier quoted context omitted.

Strong Sapir-Whorf (linguistic determinism - language constrains thought) became pretty much seen as a joke by the 1980s. Linguistic relativism (weak Sapir-Whorf - language shapes thought) is still respectable (because, I mean, of course it does). Actually, this research might just as well be evidence for linguistic universalism (Chomsky - language enables thought). In general linguistic philosophers have been coming…

Oftentimes I find myself understanding complex concepts before I can describe them, even internally . I am sure everyone has this, as I often read comments praising others' submissions for formulating their thoughts efficiently. So thoughts occur independent of language, but need it to be expressed and shared, even if through pictures and sounds.

Sounds like a description of understanding a concept in some latent space while not having fully verbalized it yet. (:

Re: Natural language instructions induce generalization in networks of neurons

#57

Post by ShamelessC »

cs702 wrote: post #8

TL;DR: The authors embed task instructions in a vector space with a language model, and train a sensorimotor-controlling model on top to perform tasks given the instruction embeddings. The authors find that the models generalize to previously unseen tasks, specified in natural language. Moreover, the authors show that the hidden states learn to represent task subcomponents, which helps explains why the model is able…

What is the language model pretrained on? Wouldn’t the far more robust LLM’s priors impact ability to generalize to “unseen” tasks?

Re: Natural language instructions induce generalization in networks of neurons

#58

Post by ben_w »

Jensson wrote: post #46
Workaccount2 wrote: post #39

Earlier quoted context omitted.

Compute is substrate independent. We use transistors because they are wicked fast and efficient. But a 4090 built from metal balls and wood blocks would still be able to perform all the same calculations. Or a 4090 made by drawing X's and O's on a (really massive) piece of paper. Or one made by connecting a bunch of neurons together for that matter. Saying cells can multiply doesn't really mean anything, unless is gi…

Analogue computers aren't equivalent to Turing machines.

No physical computer is a perfect Turing machine, thanks to random noise.

Analogue computers can always implement a Turing machine to within the bounds of that noise (and that's how transistors, which are really analogue devices, get used for digital signal and information processing).

A computer that used infinite-precision real numbers would be more powerful than any Turing machine, however unlimited-precision real numbers in the physical universe are prohibited by the holographic principle and the Bekenstein bound so we can't have them.

Re: Natural language instructions induce generalization in networks of neurons

#59

Post by ben_w »

KoolKat23 wrote: post #33
smokel wrote: post #20

Earlier quoted context omitted.

Hm, no. To start, cells are able to replicate themselves, whereas most silicon used today is not even close to doing so. The story you suggest seems to be built on a limited understanding of the processes involved. It's pretty hard to predict the future, especially given incorrect assumptions.

Cell division is a solved problem. Install new ram module and ctrl+c, ctrl+v from backup, done.

That's "solved" in the way that viruses "solved" life; I think we might want higher standards than that.

Un/fortunately (depending on who you ask), there's also a lot of automation being developed for every stage of the industrial processes from "where do we even look for the right rocks to get out of the ground?" to "here's the RAM chip you wanted to stick in your socket".

Re: Natural language instructions induce generalization in networks of neurons

#60

Post by mewpmewp2 »

AlecSchueler wrote: post #54
visarga wrote: post #35

Earlier quoted context omitted.

> a machine was built that writes like a human But the real hero here is not the LLM, but the training set. It took ages to collect all the knowledge, ideas and methods we put in books. It cost a lot of human effort to provide the data. Without the data we would have nothing. Without GPT we could use RWKV, Mamba, S4, etc and still get similar results. It's the data not the model. > the intuition that language is cent…

> But the real hero here is not the LLM, but the training set. And in the case of windmills the hero is the wind. But the mill is still a fantastic achievement.

But can mills easily move? No, people can, so people are still viable.
Post reply on HN