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

61–70 of 385 posts

Re: What can LLMs never do?

#61

Post by RandomLensman »

stavros wrote: post #35
Findecanor wrote: post #34

Earlier quoted context omitted.

Even if the generated text contains reasoning, could the LLM understand and apply it?

If I tell GPT-4 to print something, it understands it needs to check if my printer is turned on first and turn it on if it's not, so, yes? Also, if the generated text contains reasoning, what's your definition of "understanding"? Is it "must be made of the same stuff brains are"?

LLMs fail at so many reasoning tasks (not unlike humans to be fair) that they are either incapable or really poor at reasoning. As far as reasoning machines go, I suspect LLMs will be a dead end.

Reasoning here meaning, for example, given a certain situation or issue described being able to answer questions about implications, applications, and outcome of such a situation. In my experience things quickly degenerate into technobabble for non-trivial issues (also not unlike humans).

Re: What can LLMs never do?

#62

Post by donatj »

I have been trying to generate some text recently using the ChatGPT API. No matter how I word “Include any interesting facts or anecdotes without commenting on the fact being interesting” it ALWAYS starts out “One interesting fact about” or similar phrasing.

I have honestly spent multiple hours trying to word the prompt so it will stop including introductory phrases and just include the fact straight. I have gone so far as forbid the words “interesting”, “notable” and a few others in the prompt, and it just ignores me and uses them anyway.

I’ve tried all the different available models and 4 will once in a great while get it right. 3, 3 turbo, and even 4 turbo basically never work as I want.

Overall, it seems pretty bad at being told not to do certain things. For instance there are a number of topics I don’t want mentioned in its response, but telling it not to seems to only increase the likelihood that it will mention it, like you put the idea in its head.

Re: What can LLMs never do?

#63

Post by exe34 »

vouaobrasil wrote: post #36
exe34 wrote: post #32

Earlier quoted context omitted.

We should put you in charge, you seem to be a good person who won't misuse the position.

Well, I don't think I'd be good in charge. Obviously you are being sarcastic, though. But if I were in charge, I would ban all AI development. (Assuming anyone can be in charge at all. No one really is...)

You should ban knives too! We have an epidemic of knife crime here in the UK.

Re: What can LLMs never do?

#64

Post by MichaelZuo »

Xenoamorphous wrote: post #53
MichaelZuo wrote: post #46

Earlier quoted context omitted.

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…

To be frank the response itself indicates that you don't really get what was being asked, or maybe how to parse English conversation conventions?

I.e. It doesn't seem to answer the actual question.

They seem to be half responding to the second sentence which was a personal opinion, so I wasn't soliciting any answers about it. And half going on a tangent that seems to lead away from forming a direct answer.

Run these comment through a translation tool if your still not 100% sure after reading this.

Re: What can LLMs never do?

#65

Post by throwaway11460 »

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?”

I had ChatGPT design a programming language for a specific uncommon purpose and then use it. It's creative enough.

Re: What can LLMs never do?

#66

Post by fallingsquirrel »

donatj wrote: post #62

I have been trying to generate some text recently using the ChatGPT API. No matter how I word “Include any interesting facts or anecdotes without commenting on the fact being interesting” it ALWAYS starts out “One interesting fact about” or similar phrasing. I have honestly spent multiple hours trying to word the prompt so it will stop including introductory phrases and just include the fact straight. I have gone so…

I just tried this locally with llama3-8b and it handled it fine. Claude 3 Sonnet passes your test too, in case you don't have the hardware for a local model. You might want to consider moving on from ChatGPT since their models have been RLHF'd to hell in the name of "safety" and are falling behind in many ways as a result.

---

transcript:

$ ollama run llama3:8b

>>> tell me an interesting fact about etymology

Here's one:

Did you know that the word "quarantine" has a fascinating etymological history?

The word "quarantine" comes from^C

>>> tell me an interesting fact about etymology. just the fact, don't mention it's interesting.

The word "robot" originated from the Czechoslovakian word "robota," which means "forced labor" or "drudgery." This term was used in Karel Čapek's 1920 play "R.U.R." (Rossum's Universal Robots), where it referred to artificial workers.

Re: What can LLMs never do?

#67

Post by stavros »

RandomLensman wrote: post #61
stavros wrote: post #35

Earlier quoted context omitted.

If I tell GPT-4 to print something, it understands it needs to check if my printer is turned on first and turn it on if it's not, so, yes? Also, if the generated text contains reasoning, what's your definition of "understanding"? Is it "must be made of the same stuff brains are"?

LLMs fail at so many reasoning tasks (not unlike humans to be fair) that they are either incapable or really poor at reasoning. As far as reasoning machines go, I suspect LLMs will be a dead end. Reasoning here meaning, for example, given a certain situation or issue described being able to answer questions about implications, applications, and outcome of such a situation. In my experience things quickly degenerate i…

If you're contending that LLMs are incapable of reasoning, you're saying that there's no reasoning task that an LLM can do. Is that what you're saying? Because I can easily find an example to prove you wrong.

Re: What can LLMs never do?

#68

Post by vouaobrasil »

exe34 wrote: post #63
vouaobrasil wrote: post #36

Earlier quoted context omitted.

Well, I don't think I'd be good in charge. Obviously you are being sarcastic, though. But if I were in charge, I would ban all AI development. (Assuming anyone can be in charge at all. No one really is...)

You should ban knives too! We have an epidemic of knife crime here in the UK.

Knives are significantly more useful than LLMs, which are long past the point of diminishing returns.

Re: What can LLMs never do?

#69

Post by HarHarVeryFunny »

hackinthebochs wrote: post #51
HarHarVeryFunny wrote: post #39

Earlier quoted context omitted.

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?

Some limit's are pretty obvious, even if easy to fix.

For example, a pure LLM is just a single pass through a stack of transformer layers, so there is no variable depth/duration (incl. iteration/looping) of thought and no corresponding or longer duration working memory other than the embeddings as they pass thru. This is going to severely limit their ability to plan and reason since you only get a fixed N layers of reasoning regardless of what they are asked.

Lack of working memory (really needs to be context duration, or longer, not depth duration) has many predictable effects.

No doubt we will see pure-transformer architectures extended to add more capabilities, so I guess the real question is how far these extensions (+scaling) will get us. I think one thing we can be sure of though is that it won't get us to AGI (defining AGI = human-level problem solving capability) unless we add ALL of the missing pieces that the brain has, not just a couple of the easy ones.

Re: What can LLMs never do?

#70

Post by thom »

I have no beef with the actual content or conclusions, but it’s a shame the article is framed the way it is, because I don’t think we can rigorously define the goalposts for what qualifies as a future LLM. It could just as easily have been titled “Exciting avenues of research for future LLMs!” but we’re all so jaded despite the frankly astonishing progress of recent years.
Post reply on HN