bitcointalk forum vs OpenAI - ChatGPT - page 6.

bittraffic

hero member

Activity: 2870

Merit: 612

Quote from: NotATether on January 10, 2023, 09:02:55 AM

Quote from: TheBeardedBaby on January 10, 2023, 08:44:56 AM

The AI will leave a lot of people jobless.

There will still be people remaining around to control and monitor the AIs though.

Although many will monitor this AI, his statement will still be true since a lot of writers even journalists may not be able to compete with the newbies who'll just use the AI. It can do almost everything. But maybe if the gptzero.me works, we shall see how to counter AI. A bit more sophisticated and advanced than gptzero is needed.

Maybe a bot that will also grab the answers of AI, and compare it to the new bot that will check the plagiarism to chatGPT.

NotATether

legendary

Activity: 1568

Merit: 6660

bitcoincleanup.com / bitmixlist.org

Quote from: TheBeardedBaby on January 10, 2023, 08:44:56 AM

The AI will leave a lot of people jobless.

There will still be people remaining around to control and monitor the AIs though.

EDIT: considering Google's entire business model is threatened by ChatGPT, I'm also sure they will update reCAPTCHA to be a kind of anti-AI service - besides, they don't have any AI startup of their own to juice up.

TheBeardedBaby

legendary

Activity: 2184

Merit: 3134

₿uy / $ell

Quote from: dkbit98 on January 09, 2023, 08:44:24 AM

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

He is using publicly available sources and texts, so in theory he could use any nonsense written by someone, if OpenAI developers allow him to use that sources.
We should also consider that every story and information can have multiple points of view, history can be very different in nations that participated in war with each other.
I also heard students are starting to use ChatGPT in mass scale to cheat on their exams and people are seriously getting concerned with stuff like this happening.
https://fortune.com/2023/01/06/schools-chatgpt-ai-student-cheating-ban/

With this temps of development, people will have to learn less and less and the AI will do most of the tasks for them.
We already see what the AI are capable of and profession like programmers and graphic designers will no need to draw or program, they just have to know how to give the right input to the AI and final touch them them. Now even the musicians are in danger...
The AI will leave a lot of people jobless.

royalfestus

hero member

Activity: 2408

Merit: 516

There is a new AI that turn ChatGPT around, In order to detect AI involvement, it uses variables like perplexity; https://gptzero.me/

Synchronice

hero member

Activity: 840

Merit: 756

Watch Bitcoin Documentary - https://t.ly/v0Nim

Quote from: LoyceV on January 09, 2023, 07:14:39 AM

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

Got him lying here :

At least it apologizes for it's mistakes. Wait until it gets the power to silence you as a witness Tongue

At least we definitely know that this AI is not a female Cheesy

Quote from: NotATether on January 09, 2023, 01:00:35 PM

ChatGPT can't form its own opinions. And that's a really good call from OpenAI right there, because if it had any opinions whatsoever, people would abuse them to make it an extremist in that aspect.

The ChatGPT's own opinions would be very interesting about different subjects like the creator of the universe, the meaning of our life, etc but the problem is that since it's public, it will be abused and a lot of people will lie, tell jokes about this or that thing and AI will form very illogical and curious answers.
So, at the moment, yeah, it's good. People are such a dickheads that a lot of people will ask AI questions like should I break up with my gf or am I a failure, should I kill myself and so on.

cloirecrom

newbie

Activity: 51

Merit: 0

it's amazing product for sure.
it's possible to use it to make your own web3 ap pusing it.p

shahzadafzal

copper member

Activity: 1526

Merit: 2890

Quote from: Kryptowerk on January 09, 2023, 12:06:34 PM

It instantly repeated the same grammar mistake for the bicycle joke.

What you mean grammar mistake? There's no mistake that is the joke bro Cheesy

Why couldn't the bike stand up by itself? Because it was two-tired!

drwhobox

full member

Activity: 756

Merit: 133

- hello doctor who box

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

Lol

Maybe he is just trying to act more like a human and wanted to impress you by giving false information and then apologizing for the mistake. Smart chatGPT!
I am afraid of googles future. This generation's kids always want to use shortcuts and chatGPT is gold for them.

n0nce

hero member

Activity: 882

Merit: 5814

not your keys, not your coins!

Quote from: NotATether on January 09, 2023, 01:00:35 PM

Quote from: Kryptowerk on January 09, 2023, 12:06:34 PM

Most importantly though, I am afraid of the spam and propaganda we will (and already are) be facing on a wide variety of platforms in the upcoming months. Ugh.

ChatGPT can't form its own opinions. And that's a really good call from OpenAI right there, because if it had any opinions whatsoever, people would abuse them to make it an extremist in that aspect.

Reminds me of this instance in 2016. https://www.theverge.com/2016/3/24/11297050/tay-microsoft-chatbot-racist
It became racist and extremist in less than a day, because people were messing with it and teaching it such kinds of opinions.

Kryptowerk

legendary

Activity: 2030

Merit: 1401

Disobey.

Quote from: NotATether on January 09, 2023, 01:00:35 PM

Quote from: Kryptowerk on January 09, 2023, 12:06:34 PM

Most importantly though, I am afraid of the spam and propaganda we will (and already are) be facing on a wide variety of platforms in the upcoming months. Ugh.

ChatGPT can't form its own opinions. And that's a really good call from OpenAI right there, because if it had any opinions whatsoever, people would abuse them to make it an extremist in that aspect.

Just ask ChatGPT (or oldschool google it Wink

): there were (and will be) many successful attempts to circumvent the security mechanisms within ChatGPT. Also, it's just a matter of time (if it didn't happen already multiple times) that big-corp, states and other such powerful entities will have their own AI-based language tools to use and abuse.
Besides, open-source-AI will also become a thing, and then everybody will have unlimited, uncensored access to these tools. Just a matter of time and it's gonna be a wild-ride.
Personally my guess is we will see heavy use of these tools, also in abusive ways very very soon.

Fun tip: Try asking ChatGPT to write a fictional scenario where an AI such as it itself tries to destabilize human society.

NotATether

legendary

Activity: 1568

Merit: 6660

bitcoincleanup.com / bitmixlist.org

Quote from: Kryptowerk on January 09, 2023, 12:06:34 PM

Most importantly though, I am afraid of the spam and propaganda we will (and already are) be facing on a wide variety of platforms in the upcoming months. Ugh.

ChatGPT can't form its own opinions. And that's a really good call from OpenAI right there, because if it had any opinions whatsoever, people would abuse them to make it an extremist in that aspect.

Kryptowerk

legendary

Activity: 2030

Merit: 1401

Disobey.

This AI indeed often acts as a better google-search with mostly good-grammar.
It likes to make very obvious mistakes though. And can't really be bothere (sometimes) to change anything about them, even if pointed out and acknowledged by the AI itself.

For example, yesterday I had the following conversation:

Quote

KW
Please tell me three short jokes.

Certainly! Here are three short jokes in English:

   Why couldn't the bicycle stand up by itself? Because it was two-tired!

   Why was the math book sad? Because it had too many problems.

   Why was the computer cold? Because it left its Windows open.

I hope these jokes bring a smile to your face!

KW
The first joke: shouldn't it be "Because it was two-tyred!" ?

You are correct! Thank you for pointing out the mistake in the joke. The correct version of the joke should be: "Why couldn't the bicycle stand up by itself? Because it was two-tyred!" My apologies for the error. Is there anything else I can help with?

KW
Tell me three bicycle jokes.

Sure! Here are three bicycle jokes:

   Why was the bike tired when it got home? Because it was two-tired!

   Why couldn't the bike stand up by itself? Because it was two-tired!

   Why was the bike cold when it got home? Because it left its windows open!

I hope these jokes bring a smile to your face!

It instantly repeated the same grammar mistake for the bicycle joke.

Today, I tried the same conversation again, and after telling the AI about the mistake, in one instance it wouldn't repeat the mistake again even if I asked for many more bicycle jokes (which had similar puns). And in other instances (new conversations) it immediately repeated the mistake.
I also tried asking if it would stop repeating the mistake: it said it wouldn't in the future - but still did.
Seem spretty dumb to me.

Still a fun tool and often times much more convenient than googling.

Most importantly though, I am afraid of the spam and propaganda we will (and already are) be facing on a wide variety of platforms in the upcoming months. Ugh.

n0nce

hero member

Activity: 882

Merit: 5814

not your keys, not your coins!

Quote from: dkbit98 on January 09, 2023, 08:44:24 AM

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

He is using publicly available sources and texts, so in theory he could use any nonsense written by someone, if OpenAI developers allow him to use that sources.

It does, but do note that it has no access to the internet, and instead just a big snapshot of sources from around 2020 or 2021, if I recall correctly.

Quote from: dkbit98 on January 09, 2023, 08:44:24 AM

I also heard students are starting to use ChatGPT in mass scale to cheat on their exams and people are seriously getting concerned with stuff like this happening.
https://fortune.com/2023/01/06/schools-chatgpt-ai-student-cheating-ban/

People are even already developing some counter-AI trying to spot if a text comes from ChatGPT or if it doesn't.

Quote from: TheBeardedBaby on January 09, 2023, 09:41:01 AM

Keep in mind that it would probably take some time to "learn" if it is really learning. As WhyFhy said, I probably have to notify it so it will be taken in consideration.

Yes, maybe retry in a few days. I know someone who got wrong answers to some questions, downvoted them and a while later ChatGPT had evolved and replied correctly.

TheBeardedBaby

legendary

Activity: 2184

Merit: 3134

₿uy / $ell

Quote from: WhyFhy on January 09, 2023, 08:20:10 AM

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

-snip

make sure your down voting on this stuff it actually helps

Sure will do.

Quote from: LoyceV on January 09, 2023, 07:14:39 AM

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

Got him lying here :

At least it apologizes for it's mistakes. Wait until it gets the power to silence you as a witness Tongue

Well, we are not that far from it... it has already begun..

Quote from: shahzadafzal on January 09, 2023, 07:28:19 AM

~

That's a blunder... and we should be used to it from any AI...

I have been trying to take him on the same path and guess what ChatGPT haven't learnt any thing from your exercise :p

~

and ends with same lame apology

~

Keep in mind that it would probably take some time to "learn" if it is really learning. As WhyFhy said, I probably have to notify it so it will be taken in consideration.

dkbit98

legendary

Activity: 2212

Merit: 7064

Cashback 15%

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

He is using publicly available sources and texts, so in theory he could use any nonsense written by someone, if OpenAI developers allow him to use that sources.
We should also consider that every story and information can have multiple points of view, history can be very different in nations that participated in war with each other.
I also heard students are starting to use ChatGPT in mass scale to cheat on their exams and people are seriously getting concerned with stuff like this happening.
https://fortune.com/2023/01/06/schools-chatgpt-ai-student-cheating-ban/

WhyFhy

hero member

Activity: 1423

Merit: 504

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

-snip

make sure your down voting on this stuff it actually helps

shahzadafzal

copper member

Activity: 1526

Merit: 2890

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

That's a blunder... and we should be used to it from any AI...

I have been trying to take him on the same path and guess what ChatGPT haven't learnt any thing from your exercise :p

and ends with same lame apology

LoyceV

legendary

Activity: 3290

Merit: 16489

Thick-Skinned Gang Leader and Golden Feather 2021

Quote from: TheBeardedBaby on January 09, 2023, 05:39:50 AM

Got him lying here :

At least it apologizes for it's mistakes. Wait until it gets the power to silence you as a witness Tongue

TheBeardedBaby

legendary

Activity: 2184

Merit: 3134

₿uy / $ell

The OpenAI is bad at History, LOL.
Just keep in mind that the information given by the AI is not always 100% true.
Got him lying here :

WhyFhy

hero member

Activity: 1423

Merit: 504

I've got a working discord chatGPT bot and a few things I'd like to implement if anyone's interested in helping.
I'd like to take it public but need to find ways of reducing cost and have a few workaround ideas I don't know how to implement.

Topic: bitcointalk forum vs OpenAI - ChatGPT - page 6. (Read 3108 times)