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

Hallucination is inevitable: An innate limitation of large language models

arxiv.org

Post reply on HN
Print view View original

331–340 of 491 posts

Re: Hallucination is inevitable: An innate limitation of large language models

#331

Post by Jensson »

steveBK123 wrote: post #323
digitalsushi wrote: post #199

Earlier quoted context omitted.

'Adjust accordingly' includes giving up and delivering something similar to what I asked, but not what I asked; is this the point at which the circle is complete and AI has fully replaced my dev team?

Everyone assumes the AI is going to replace their employees but not replace them.. fascinating.

Uber proves we can replace Taxi management with simple algorithms, that was apparently much easier than replacing the drivers. I hope these bigger models can replace management in more industries, I'd love to have an AI as a manager.

Re: Hallucination is inevitable: An innate limitation of large language models

#332

Post by cultureswitch »

mannykannot wrote: post #155
MuffinFlavored wrote: post #139

Earlier quoted context omitted.

how did LLMs get this far without any concept of understanding? how much further can they go until they become “close enough”?

This is a fair question: LLMs do challenge the easy assumption (as made, for example, in Searle's "Chinese Room" thought experiment) that computers cannot possibly understand things. Here, however, I would say that if an LLM can be said to have understanding or knowledge of something, it is of the patterns of token occurrences to be found in the use of language. It is not clear that this also grants the LLM any under…

Should it matter how the object of debate interacts and probes the external world? We sense the world through specialized cells connected to neurons. There's nothing to prevent LLMs doing functionally the same thing. Both human brains and LLMs have information inputs and outputs, there's nothing that can go through one which can't go through the other.

Re: Hallucination is inevitable: An innate limitation of large language models

#333

Post by bonzaidrinkingb »

nedt wrote: post #310

Well humans believe that vacination either kills people or gives them chips for tracking and the top politicians are lizard people drinking the blood of children kept in caves and they had to fake a pandemic to get them out. I'd say an A.I. hallucinating isn't that far off from real humans. It's rather the recipient that needs to interpret any response from either.

Around 12k fatal outcomes have been reported in the EU after vaccination, but it is not certain in all cases that vaccines were the cause.

The vaccine tracking chips come from two Microsoft (-affiliate) patents, one about using chips to track body activity to reward in cryptocurrency, and another about putting a vaccine passport chip in the hands of African immigrants. That vaccines contain tracking chips is a fabricated conspiracy to ridicule and obfuscate.

Lizard people is often an anti-semitic dog whistle.

Rich elites use blood transfusions of young people to combat aging and age-related disease.

Children have been kept in cages and feral children have lived in caves.

You likely made up the part about faking a pandemic to get children out of caves, unless you can point to discussion about these beliefs.

Real humans do hallucinate all the time.

Re: Hallucination is inevitable: An innate limitation of large language models

#334

Post by jijijijij »

jncfhnb wrote: post #308
sandworm101 wrote: post #163

Earlier quoted context omitted.

They cannot say "I dont know" because they dont actually know anything. The answers are not comming from a thinking mind but a complex pattern-fitting supercomputer hovering over a massive table of precomputed patterns. It computes your input then looks to those patterns and spits out the best match. There is no thinking brain with a conceptual understanding of its own limitations. Getting an "i dont know" from curre…

> They cannot say "I dont know" because they dont actually know anything. print(“I don’t know”) You don’t need proper cognition to identify that the answer is not stored in source data. Your conception of the model is incomplete as is easily demonstrable by testing such cases now. Chat gpt does just fine on your simpsons test. You, however, have made up an answer of how something works that you don’t actually know de…

> to identify that the answer is not stored in source data

How would an LLM do that?

Re: Hallucination is inevitable: An innate limitation of large language models

#335

Post by Jensson »

tgv wrote: post #246
Jensson wrote: post #97

Earlier quoted context omitted.

But there are many pieces of code that I've written that you can find in many places on the net, having a tool that can adapt that to your codebase in seconds is useful. It doesn't have to be smart, just pasting in an function and fitting that to your code is useful.

Sure, but the point is it will have to adapt it to your code, if only in naming. So it has to make up things, i.e. hallucinate. It can't just reproduce the best match in memory.

Yeah, these models are very good at making up names, that is what they are trained to do after all. Their ability to do logic isn't that impressive though and seems to be on the level of a human that doesn't understand the topic but has seen many examples.

Re: Hallucination is inevitable: An innate limitation of large language models

#336

Post by cultureswitch »

solarhexes wrote: post #202
ninetyninenine wrote: post #188

Earlier quoted context omitted.

Explain sora. It must have of course a blurry understanding of reality to even produce those videos. I think we are way past the point of debate here. LLMs are not stochastic parrots. LLMs do understand an aspect of reality. Even the LLMs that are weaker than sora understand things. What is debatable is whether LLMs are conscious. But whether it can understand something is a pretty clear yes. But does it understand e…

If by “understand” you mean “can model reasonably accurately much of the time” then maybe you’ll find consensus. But that’s not a universal definition of “understand”. For example, if I asked you whether you “understand” ballistic flight, and you produced a table that you interpolate from instead of a quadratic, then I would not feel that you understand it, even though you can kinda sorta model it. And even if you do…

Are you telling me that WW1 artillery crews didn't understand ballistics? Because they were using tables.

There's no difference between doing something that works without understanding and doing the exact same thing with understanding.

Re: Hallucination is inevitable: An innate limitation of large language models

#337

Post by nedt »

katehikes88 wrote: post #313
nedt wrote: post #310

Well humans believe that vacination either kills people or gives them chips for tracking and the top politicians are lizard people drinking the blood of children kept in caves and they had to fake a pandemic to get them out. I'd say an A.I. hallucinating isn't that far off from real humans. It's rather the recipient that needs to interpret any response from either.

Have you considered that parts of what you said might be true but you ridicule it only because you associate with the others might be untrue and maybe even ridiculous?

It might be true, or not. It might be ridiculous, or not. With _it_ being a message from a human or an AI. A hallucination is not so much a problem as long as there is not blind trust or a single source of truth. And oh boy would I like to be pure ridiculous or satirical with the example of what humans are believing.

Re: Hallucination is inevitable: An innate limitation of large language models

#338

Post by dragonwriter »

bonzaidrinkingb wrote: post #333
nedt wrote: post #310

Well humans believe that vacination either kills people or gives them chips for tracking and the top politicians are lizard people drinking the blood of children kept in caves and they had to fake a pandemic to get them out. I'd say an A.I. hallucinating isn't that far off from real humans. It's rather the recipient that needs to interpret any response from either.

Around 12k fatal outcomes have been reported in the EU after vaccination, but it is not certain in all cases that vaccines were the cause. The vaccine tracking chips come from two Microsoft (-affiliate) patents, one about using chips to track body activity to reward in cryptocurrency, and another about putting a vaccine passport chip in the hands of African immigrants. That vaccines contain tracking chips is a fabric…

> Real humans do hallucinate all the time.

No, they don't hallucinate “all the time”, but LLM “hallucination” is a bad metaphor, as the phenomenon is more like confabulation than hallucination.

Humans also don’t confabulate all the time, either, though.

Re: Hallucination is inevitable: An innate limitation of large language models

#339

Post by jijijijij »

fl7305 wrote: post #201
sandworm101 wrote: post #163

Earlier quoted context omitted.

They cannot say "I dont know" because they dont actually know anything. The answers are not comming from a thinking mind but a complex pattern-fitting supercomputer hovering over a massive table of precomputed patterns. It computes your input then looks to those patterns and spits out the best match. There is no thinking brain with a conceptual understanding of its own limitations. Getting an "i dont know" from curre…

> a complex pattern-fitting supercomputer hovering over a massive table of precomputed patterns That was perhaps true of earlier and smaller LLMs, like GPT-1 and GPT-2. But as they grew larger and were trained with more and more data, they changed from pure pattern matching to implementing algorithms to compress more information into their structure than pure pattern matching can achieve. These algorithms are incompl…

Hasn't ChatGPT been manually adjusted to better compute math problems? I think nobody not working there knows what ChatGPT really learned all by itself.

Re: Hallucination is inevitable: An innate limitation of large language models

#340

Post by ericb »

skywhopper wrote: post #275
digitalsushi wrote: post #199

Earlier quoted context omitted.

'Adjust accordingly' includes giving up and delivering something similar to what I asked, but not what I asked; is this the point at which the circle is complete and AI has fully replaced my dev team?

One thing a human might do that I’ve never seen an LLM do is ask followup and clarifying questions to determine what is actually being requested.

What makes this fascinating to me is, these LLM's were trained on an internet filled with tons of examples of humans asking clarifying questions.

Why doesn't the LLM do this? Why is the "next, most-likely token" never a request for clarification?

Post reply on HN