[CactusOnFire]

Because ChatGPT is so new, we are in this weird period where people haven't learned that is just as incorrect as the rest of us.

I am hoping that in a year from now people will be more skeptical of what they hear from conversational AI. But perhaps that is optimistic of me.

[Xylakant]

> Because ChatGPT is so new, we are in this weird period where people haven't learned that is just as incorrect as the rest of us.

It’s worse than that. It’s wrong, you cannot correct it and it makes up supporting citations on the fly. Very few humans behave like that.

[TehCorwiz]

I can think of more than a few that regularly appear on TV.

[Xylakant]

So can I, but luckily TV is not representative of the world at large.

[BeFlatXIII]

I can think of one who was once in the White House.

[gyudin]

You've described pretty much every politician or any doctor that posses outdated information

https://www.economist.com/science-and-technology/2023/02/22/...

[renewiltord]

I think very many humans behave like that, actually. A recent example is people claiming that Flint, MI still has leaded water.

But in the past, HN users "corroborated" that Apple is spying on them etc. Fabrication is well and alive among us.

[nl]

> A recent example is people claiming that Flint, MI still has leaded water.

Doesn't it?

According to [1]:

The residential lead service line replacement was initially set to be finished in 2019, according to a settlement agreement with the city. That deadline was eventually pushed back to the fall of 2022 and has most recently been set for completion in August 2023, according to city officials.

and

"More than 95% of lead pipes in Flint have been replaced, and we will continue the work until the job is done," Flint Mayor Sheldon Neeley said in a recent statement on the water filters.

It sounds to me a lot like Flint, MI still has leaded water?

[1] https://abcnews.go.com/US/flint-residents-urged-filter-water...

[renewiltord]

Fair point. Which makes these humans (and me, I suppose) like ChatGPT:

https://twitter.com/BeijingPalmer/status/1628585234865262593...

https://twitter.com/SCPantera/status/1127416274550546432

So ChatGPT isn't all that different from people.

[Xylakant]

No, the fundamental difference is that you can reason about your mistake, can correct yourself and try to avoid falling into the same trap again. You are capable of independent thought. ChatGPT string words together.

[renewiltord]

Perhaps not ChatGPT, though it does show admirable skill, but it seems quite likely that its successors may well be able to do that through sheer size.

Certainly, in many conversations with ChatGPT, it is indistinguishable from a human changing their mind.

Since the process of "reasoning" is not particularly well understood, it seems a bit premature to declare it different from LLMs.

[nl]

Those tweets are a lot less specific though. In general the government did fix it and the water is safe. But specifically there are still 5% of pipes that have lead in them (but apparently thesr are ones that are generally not for domestic supply or something).

So the exact claim matters a lot.

[renewiltord]

My comment was certainly wrong right off, though. I, a human, bullshitted just like ChatGPT.

[krainboltgreene]

I'm so interested to find out how you learned this lie and why you decided to believe it over the people who live there.

[renewiltord]

Certainly. It's from an erroneous inversion by me of this line https://twitter.com/beijingpalmer/status/1628585234865262593...

I interpreted "Flint has clean water" as "Flint doesn't have leaded water". But of course, one doesn't mean the other.

A classic example of me, a human, behaving like ChatGPT.

[austinshea]

It’s not incorrect like the rest of us. It’s incorrect in a very different way.

Providing detailed information on the usage of a service that has never existed is a brand new kind of incorrect that is carelessly causing the rest of us grief.

[fijiaarone]

Every technology devolves to TV. The fact that you have to not only read, but write to interact with ChatGPT means 99.99% of people will not use it.

I trust Alexa & Siri completely though.

[flangola7]

Hook it up to fMRI

[none_to_remain]

Humans are capable of not bullshitting

ChatGPT can only bullshit

[avgDev]

It is quite interesting really. I took AI in school but I have not dived deep at all in ChatGPT but isn't chatGpt just learning from the internet?

Could someone push "wrong" opinion heavily online to sway the opinion of AI?

I can only imagine a bot that learned from 4chan.

[ChatGTP]

Meet gpt-4chan https://huggingface.co/ykilcher/gpt-4chan

Dreams can come true…

[ravenstine]

AI will never be totally correct. If it ever is, then we've found God.

[GulpGulp]

I think some of this will take care of itself with attrition. People who lack the knowledge to fact check on the fly will give up after repeatedly getting wrong answers.

[ChatGTP]

I’m also worried there’s so potential money involved now that it’s never going away.

Even if it’s wrong, dangerous, misleading, fundamentally flawed as a concept whatever. Big tech and money will find ways to keep putting it in front of us.

[quantiq]

I see a lot of parallels here to crypto and NFTs where people start inventing use cases for technologies that fundamentally haven’t demonstrated business value, and pray that one day business value will show up out of nowhere.

[annoyingnoob]

> just as incorrect as the rest of us

Even worse because it has no clue when it might be completely wrong and yet it will be confident in its answer.

[DoktorDelta]

That might be the most human thing it's ever done

[mdp2021]

Dunning-Kruger, provisionality and delirating are different things.