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

LLMs Will Always Hallucinate, and We Need to Live with This

arxiv.org

Post reply on HN
Print view View original

21–30 of 274 posts

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#21

Post by unshavedyak »

mxwsn wrote: post #4

OK - there's always a nonzero chance of hallucination. There's also a non-zero chance that macroscale objects can do quantum tunnelling, but no one is arguing that we "need to live with this" fact. A theoretical proof of the impossibility of reaching 0% probability of some event is nice, but in practice it says little about whether we can exponentially decrease the probability of it happening or not to effectively mi…

Plus, why do we care about that degree? If we could make it so humans don't hallucinate too that would be great, but it ain't happening. Humans memory gets polluted the moment you feed them new information, as evidence by how much care we have to give when trying to extract information when it matters, like law enforcement.

People rag on LLMs constantly and i get it, but they then give humans way too much credit imo. The primary difference i feel like we see with LLMs vs Humans is complexity. No, i don't personally believe LLMs can scale to human "intelligence". However atm it feels like comparing a worm brain to a human intelligence and saying that's evidence that neurons can't reach human intelligence level.. despite the worm being a fraction of the underling complexity.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#22

Post by kfarr »

talldayo wrote: post #8
panarky wrote: post #6

Earlier quoted context omitted.

Exactly. LLMs will sometimes be inaccurate. So are humans. When LLMs are clearly better than humans for specific use cases, we don't need 100% perfection. Autonomous cars will sometimes cause accidents. So do humans. When AVs are clearly safer than humans for specific driving scenarios, we don't need 100% perfection.

> When AVs are clearly safer than humans for specific driving scenarios, we don't need 100% perfection. People didn't stop refining the calculator once it was fast enough to beat a human. It's reasonable to expect absolute idempotent perfection from a robot designed to manufacture text.

Not sure absolute perfection is a concept that can exist in the universe of words.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#24

Post by zer00eyz »

Shakes fist at clouds... Back in my day we called these "bugs" and if you didn't fix them your program didn't work.

Jest aside, there is a long list of "flaws" in LLMS that no one seems to be addressing. Hallucinations, Cut off dates, Lack of true reasoning (the parlor tricks to get there don't cut it), size/cost constraints...

LLM's face the same issues as expert systems, without the constant input of experts (subject matter) your llm becomes quickly outdated and useless, for all but the most trivial of tasks.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#26

Post by tourmalinetaco »

talldayo wrote: post #8
panarky wrote: post #6

Earlier quoted context omitted.

Exactly. LLMs will sometimes be inaccurate. So are humans. When LLMs are clearly better than humans for specific use cases, we don't need 100% perfection. Autonomous cars will sometimes cause accidents. So do humans. When AVs are clearly safer than humans for specific driving scenarios, we don't need 100% perfection.

> When AVs are clearly safer than humans for specific driving scenarios, we don't need 100% perfection. People didn't stop refining the calculator once it was fast enough to beat a human. It's reasonable to expect absolute idempotent perfection from a robot designed to manufacture text.

Maybe, down the line. The calculator went through a long period of perfecting until it became as powerful as they are today. It’s only natural LLMs will also take time. And much like calculators moving from stepped drums, to vacuum tubes, to finally transistors, the way we build LLMs are sure to change. Although I’m not quite sure idempotence is something LLMs are capable of.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#27

Post by danenania »

Perplexity does a pretty good job on this. I find myself reaching for it first when looking for a factual answer or doing research. It can still make mistakes but the hallucination rate is very low. It feels comparable to a google search in terms of accuracy.

Pure LLMs are better for brainstorming or thinking through a task.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#28

Post by christianqchung »

TheGeminon wrote: post #16
everdrive wrote: post #10

Earlier quoted context omitted.

One big difference is that at least some people have a healthy sense for when they may be wrong. This sort of meta-cognitive introspection is currently not possible for an LLM. For instance, let's say I asked someone "do you know the first 10 elements of the periodic table of elements?" Most people would be able to accurately say "honestly I'm not sure what comes after Helium." But an LLM will just make up some bulls…

There are ways to gauge the confidence of the LLM (token probabilities over the response, generating multiple outputs and checking consistency), but yeah that’s outside the LLM itself. You could feed the info back to the LLM as a status/message I suppose

The problem is also that the model may have a very high confidence in token probability and is still wrong, but I'm sure it could help in some cases.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#29

Post by amelius »

mxwsn wrote: post #4

OK - there's always a nonzero chance of hallucination. There's also a non-zero chance that macroscale objects can do quantum tunnelling, but no one is arguing that we "need to live with this" fact. A theoretical proof of the impossibility of reaching 0% probability of some event is nice, but in practice it says little about whether we can exponentially decrease the probability of it happening or not to effectively mi…

> there's always a nonzero chance of hallucination. There's also a non-zero chance that macroscale objects can do quantum tunnelling, but no one is arguing that we "need to live with this" fact.

True, but it is defeatist and goes against a good engineering/scientific mindset.

With this attitude we'd still be practicing alchemy.

Re: LLMs Will Always Hallucinate, and We Need to Live with This

#30

Post by The_Colonel »

everdrive wrote: post #10
bicx wrote: post #3

I treat LLMs like a fallible being, the same way I treat humans. I don’t just trust output implicitly, and I accept help with tasks knowing I am taking a certain degree of risk. Mostly, my experience has been very positive with GPT-4o / ChatGPT and GitHub copilot with that in mind. I use each constantly throughout the day.

One big difference is that at least some people have a healthy sense for when they may be wrong. This sort of meta-cognitive introspection is currently not possible for an LLM. For instance, let's say I asked someone "do you know the first 10 elements of the periodic table of elements?" Most people would be able to accurately say "honestly I'm not sure what comes after Helium." But an LLM will just make up some bulls…

That's indeed the biggest problem, because it limits its usefulness to questions for which you can verify the correctness. (Don't get me wrong, you can still get a lot of utility out of that, since for many problems finding the [candidate] solutions is much more difficult than verifying them)

OT, but this also reminds me how much I despise bullshitters. Sometimes right, something wrong, but always confident. In the end, you can't trust what they say.

Post reply on HN