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

351–360 of 385 posts

Re: What can LLMs never do?

#351

Post by marquisdepolis »

pbhjpbhj wrote: post #171
tobiasSoftware wrote: post #155

Earlier quoted context omitted.

"I find it useful to think “what can I expect from speaking with the dataset of combined writing of people”, rather than treating a basic LLM as a mind." I've been doing this as well, mentally I think of LLMs as the librarians of the internet.

They're bad librarians. They're not bad, they do a bad job of being librarians, which is a good thing! They can't quite tell you the exact quote, but they do recall the gist, they're not sure it was Gandhi who said that thing but they think he did, it might be in this post or perhaps one of these. They'll point you to the right section of the library to find what you're after, but make sure you verify it!

They are librarians, just that it happens to be the library of Babel.

Re: What can LLMs never do?

#352

Post by marquisdepolis »

shawntan wrote: post #71

If we're trying to quantify what they can NEVER do, I think we'd have to resort to some theoretical results rather than a list empirical evidence of what they can't do now. The terminology you'd look for in the literature would be "expressibility". For a review of this topic, I'd suggest: https://nessie.ilab.sztaki.hu/~kornai/2023/Hopf/Resources/st... The authors of this review have themselves written several article…

This is very interesting thanks Shawn. I did email William Merrill to see his thoughts but didn't get a response yet.

Re: What can LLMs never do?

#353

Post by marquisdepolis »

wave_1 wrote: post #105

I build an Agentic AI that leverages #6 and #7 at the end of the article as well as techniques not yet published. It tackles hallucination relative not to the world at large but to the facts, entities and causal relationships contained in a document (which is really bad reasoning if we assume LLMs are "reasoning" to begin with) It also tackles cross-reasoning with very large token distance. https://www.youtube.com/wa…

Author here. This is super interesting, and while I am mostly a lurker here welcome back?

Re: What can LLMs never do?

#354

Post by Eridrus »

Starting with the reversal curse is weird since there is a simple workaround to this, which is to identify entity names to keep them in their proper order, and then train on the reverse of the pretraining corpus: https://arxiv.org/abs/2403.13799v1

You can argue about how this doesn't really say anything surprising since the reversal of "A is B" is literally "B is A", but it's weird to expect elegant solutions to all problems on all fronts all at once, and we do have an incredibly simple data generation process here.

Re: What can LLMs never do?

#355

Post by thrdbndndn »

> LLMs are hard to, as I've written multiple times, and their ability to reason is difficult to separate from what they're trained on.

Can someone explain this sentence to me? It looks broken (hard to what?).

Re: What can LLMs never do?

#356

Post by dragonwriter »

coffeebeqn wrote: post #325
dragonwriter wrote: post #135

Earlier quoted context omitted.

That would like saying that because humans’ output can be better or worse based on better or worse past experience (~prompting, in that it is the source of the equivalent of “in-context learning”), humans lack general intelligence.

This is more like the distinction of a Jr and Sr dev. One needs the tasks the be pre-chewed and defined “good prompts” while the latter can deal with very ambiguous problems

The entirety of a human's experience is the “prompt”. Current LLMs rely on the analog of instinct (pre-context in-built training) a lot more than humans for their behavior because they have itty bitty tiny context windows, but humans have really big context windows for in-context learning.

Re: What can LLMs never do?

#357

Post by kromem »

fragmede wrote: post #348
kromem wrote: post #309

Earlier quoted context omitted.

Mine is also the river crossing puzzle. What's your variation?

the boat is big enough to hold all the items I asked it > lion, goat, wolf riddle, but the boat is big enough to carry all of them and it said it could do it in one step. https://chat.openai.com/share/7b7a5462-7649-403d-a4f0-01c387... ChatGPT-4 today (April 28th, 2024) still fails at it sometimes: https://chat.openai.com/share/1bec923d-d727-42fe-ba9b-9f92b9... This is ChatGPT-4 getting it wrong, months ago: https://c…

Ah, ok. My variation is it's a vegetarian wolf, a carnivorous goat, and a cabbage.

There's a few different hacks that will get it to work, but one of the more interesting is switching the nouns to emojis.

But almost none of the models ever get it on the first try, and every major model since GPT-4 can have the prompt tweaked to get it with the exception of Llama-3, which I just can't get to solve it with anything I've tried so far (and I'm not sure if it's because of extra strong associations to the standard form from the extra training run or if it lacks the core competencies, though I am starting to think it's the latter given how it responds as I point out errors).

I particularly like this variation because it requires remapping concepts in unintuitive ways based on broad abstractions, like having a goat potentially eat a wolf because of it being carnivorous.

Re: What can LLMs never do?

#358

Post by autoexec »

PopePompus wrote: post #274
Hunpeter wrote: post #268

Earlier quoted context omitted.

Yes, but our brain is still working and processing information at those times as well, isn't it? Even if not in the same way as it does when we're conscious.

What about general anesthesia? I had a major operation during which most of my brain was definitely offline for at least 8 hours.

Anesthesia shouldn't take your brain offline. It just makes you unconscious, paralyzes you, and gives you amnesia. Your brain is still active under general anesthesia. What you were thinking or feeling for those 8 hours was just forgotten.

Re: What can LLMs never do?

#359

Post by vsnf »

bxparks wrote: post #223
mkl wrote: post #180

Earlier quoted context omitted.

Much better, but still missing "than" after "greater", which seems kind of critical. "Using" is important as a number greater than ten can't be written as a digit, but can be written using digits ("with" would be just as good). Repeating "written" makes it clearer that there are two instructions.

It's funny, I didn't notice the missing "than" until much later. After I learned the intended meaning of the original sentence, my mind just seemed to insert the missing "than" automatically.

Mine as well. After understanding the meaning thanks to the other posters, the sentence magically looked fine. But before knowing the meaning, it was gibberish. I’ve become aware of this before, and it makes me wonder just how often I’m interpreting grammatical nonsense on a daily basis without realizing it.

Re: What can LLMs never do?

#360

Post by cs702 »

naasking wrote: post #339
cs702 wrote: post #310

Earlier quoted context omitted.

I agree with you, but your comment strikes me as unfair nitpicking , because the OP is referring to information that has been encoded in words.

I understand that's the context, but I'm not sure that it's unfair nitpicking. It's common to talk about training data and how poor LLMs are compared to humans despite the apparently larger dataset than any human could absorb in a lifetime. The argument is just wrong because it doesn't properly quantify the dataset size, and when you do, you actually conclude the opposite: it's astounding how good LLMs are despite th…

> I understand that's the context, but I'm not sure that it's unfair nitpicking.

The OP is about much more than that, and taken as a whole, suggests the author is well aware that human beings absorb a lot more data from multiple domains. It struck me as unfair to criticize one sentence out of context while ignoring the rest of the OP.

> It's common to talk about training data and how poor LLMs are compared to humans despite the apparently larger dataset than any human could absorb in a lifetime.

Thank you. Like I said, I agree. My sense is the author would agree too.

It's possible that to overcome some of the limits we're starting to see, AI models may need to absorb a giant, endless, torrential stream of non-textual, multi-domain data, like people.

At the moment, we don't know.

Post reply on HN