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

What can LLMs never do?

strangeloopcanon.com

Post reply on HN
Print view View original

51–60 of 385 posts

Re: What can LLMs never do?

#51

Post by hackinthebochs »

HarHarVeryFunny wrote: post #39
3abiton wrote: post #3

The article should be titled " What can LLM never do, yet". By definition, Large Language Models would keep growing larger and larger, to be trained on faster and more advanced hardware, and certain points like "completing complex chains of logical reasoning" tasks, would be just a time hurdle. Only time will tell.

We really don't need time to tell. Just making a transformer bigger and bigger, and feeding it more and more data, will not change it from being a language model into something else, anymore than scaling up an expert system such as Cyc will transform it into something other than an expert system. "Scale it up and it'll become sentient" is one of the recurring myths of AI.. a bit odd that people are falling for it aga…

>will not change it from being a language model into something else,

This is a pretty empty claim when we don't know what the limits of language modelling are. Of course it will never not be a language model. But the question is what are the limits of capability of this class of computing device?

Re: What can LLMs never do?

#52

Post by GaggiX »

>Another assumption is that it’s because of tokenisation issues. But that can’t be true either.

It's definitely a tokenizer issue, if GPT-4 was trained on singular characters I'm pretty sure it would be able to play Wordle much better. GPT-4 as they are trained today have quite lossy knowledge about the characters inside a specific token, probably a fix would be to embed the knowledge inside the embeddings.

Re: What can LLMs never do?

#53

Post by Xenoamorphous »

MichaelZuo wrote: post #46
Xenoamorphous wrote: post #21

Earlier quoted context omitted.

“Ten” is a word, “10” are digits. I’m not a native English speaker, how would you write it? FWIW the LLMs get it right many times, but fail other times.

If your not a native English speaker, why are you even expecting the LLM to understand even 80% of the time? Just ask it in your own native language.

First of all, the texts the rule has to be applied to are written in English. Second, I believe English is by far (by far) the most prevalent language in the training dataset for those models, so I’d expect it to work better at this kind of task.

And third, I’m not the only one working on this problem, there are others that are native speakers, and as my initial message stated, there have been many variations of the prompt. None work for all cases.

And lastly, how would you rewrite my sample prompt? Which BTW bad a typo (unrelated to my English skills) that I’ve now fixed.

Re: What can LLMs never do?

#54

Post by cj »

stavros wrote: post #40
rambambram wrote: post #37

Earlier quoted context omitted.

> If the text that the text-generating tool generates contains reasoning, then the text generation tool can be said to be reasoning, can't it. I don't know... you're still describing a talking parrot here, if you'd ask me.

What's the difference between a human and a talking parrot that can answer any question you ask it?

The talking parrot can only answer by repeating something it heard before.

Another question you could ask is “What’s the difference between a conversation between 2 people and a conversation between 2 parrots who can answer any question?”

Re: What can LLMs never do?

#55

Post by Xenoamorphous »

zamadatix wrote: post #38
vsnf wrote: post #20

Earlier quoted context omitted.

> ensure that numbers from one to ten as written as words and numbers greater ten as digits in the given text I can’t fault llms for not knowing what to do here because I, a human, have no idea what on earth this means.

I think you may be thrown off because the first "as" is meant to be "are".

Thanks, that was def a typo that I’ve fixed now.

Re: What can LLMs never do?

#56

Post by enraged_camel »

Yesterday I asked ChatGPT 4 to write a paragraph with exactly five unique palindromes, and for some reason it really, really struggled. First it wrote a paragraph with four palindromes, then it rewrote it but some palindromes were repeated with a total of seven, etc.

Re: What can LLMs never do?

#57

Post by smusamashah »

Do we have an open/shared list of problems that LLMs can't solve?

People have mentioned some other problems apart from those in the article. Someone should compile these and put them up if they haven't been already

Re: What can LLMs never do?

#58

Post by stavros »

cj wrote: post #54
stavros wrote: post #40

Earlier quoted context omitted.

What's the difference between a human and a talking parrot that can answer any question you ask it?

The talking parrot can only answer by repeating something it heard before. Another question you could ask is “What’s the difference between a conversation between 2 people and a conversation between 2 parrots who can answer any question?”

It doesn't only repeat things it's heard before. Have you ever talked with an LLM?

Re: What can LLMs never do?

#59

Post by oldandtired »

Far too many people (including AI researchers themselves) fail to see that all LLMs are actually simple machines. Extremely simple machines that are only mechanically following a relatively simple programming path.

Now before anyone gets too caught up with objecting to this notion, I would seriously suggest that you spend time with observing children from new-born to 2 years.

I have been observing my latest granddaughter sine her birth about 16 months ago and thinking about every public LLM system current;y available.

There is an insight here to be obtained and that insight is in the nature of real intelligence.

On the whole, no-one actually knows what intelligence is or what sentience is or what it means to be cognitively conscious. There is still much research going on and nothing actually definitive has come forth yet. We really are at the beginning in terms of studying these areas.

We can certainly produce some incredible systems, but none of them are intelligent per se. Solutions to certain kinds of problems can be achieved using these systems and there are researchers who are seriously looking at incorporating these systems into CAS and theorem provers. These systems though only provide an augmentation service for a person as does every mechanical system we use

But there is an essential component necessary for the use of all LLMs which many seem to not be cognisant of and that is these systems, to be useful, require humans to be involved.

The questions we have to ask ourselves is: what can we use these systems for and do these uses provide benefits in some way or can these systems be abused by various parties in obtaining control over others?

There are benefits and there are abuses. Can we do better or will we do worse by using them?

Re: What can LLMs never do?

#60

Post by cs702 »

cs702 wrote: post #14

Fantastic essay. Highly recommended! I agree with all key points: * There are problems that are easy for human beings but hard for current LLMs (and maybe impossible for them; no one knows). Examples include playing Wordle and predicting cellular automata (including Turing-complete ones like Rule 110). We don't fully understand why current LLMs are bad at these tasks. * Providing an LLM with examples and step-by-step…

As an aside, at one point I experimented a little with transformers that had access to external memory searchable via KNN lookups https://github.com/lucidrains/memorizing-transformers-pytorc... (great work by lucidrains) or via routed queries with https://github.com/glassroom/heinsen_routing (don't fully understand it; apparently related to attention). Both approaches seemed to work, but I had to put that work on hold for reasons outside my control.

Also as an aside, I'll add that transformers can be seen as a kind of "RNN" that grows its hidden state with each new token in the input context. I wonder if we will end up needing some new kind of "RNN" that can grow or shrink its hidden state and also access some kind of permanent memory as needed at each step.

We sure live in interesting times!

Post reply on HN