LLMs Will Always Hallucinate, and We Need to Live with This
1–10 of 274 posts
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#2We might as well embrace them: https://github.com/DivergentAI/dreamGPT
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#3I 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.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#4OK - 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 mitigate risk.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#5A key skill necessary to work effectively with LLMs is learning how to use technology that is fundamentally unreliable and non-deterministic.
A lot of people appear to find this hurdle almost impossible to overcome.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#6OK - 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…
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.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#7I'm of the opinion that the current architectures are fundamentally ridden with "hallucinations" that will severely limit their practical usage (including very much what the hype thinks they could do). But this article puts an impossible limit to what it is to "not-hallucinate".
It essentially restates well known fundamental limitations of formal systems and mechanistic computation and then presents the trivial result that LLMs also share these limitations.
Unless some dualism or speculative supercomputational quantum stuff is invoked, this holds very much to humans too.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#8OK - 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…
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.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#9I 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.
I treat them as always hallucinating and it just so happens that, by accident, they sometimes produce results that resemble intentional, considered or otherwise veritable to the human observer. The accident is sometimes of a high probability, but still an accident. Humans are similar, but we are the standard for what’s to be considered a hallucination, clinically speaking. For us, a hallucination is a cause of concern. For llms, it’s just one of all the possible results. Monkeys bashing on a typewriter. This difference is an essential one, imo.
Re: LLMs Will Always Hallucinate, and We Need to Live with This
#10I 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 bullshit, at least some of the time.