AI-generated post discussion thread: how to identify & report

[The Sceptical Chymist]

Even the best posters who are native English speakers don't necessarily write every post using the precision in punctuation, spelling & grammar executed by ChatGPT.

I am simply insulted by that statement.  Though I tend to overuse dashes, ellipses and such, I don't think that's technically against the rules of the English language.  My English is so polished that everyone else's looks like a blow-up sex doll covered in bodily fluids by comparison.  I dare you or anyone else to find a post I've made that contains misspellings, missing or incorrect punctuation, run-on sentences, or any of the major pitfalls for those who just can't handle the language.  In addition, my vocabulary is extensive and I've gotten PMs of praise from non-native English speakers because of my word selection.  *Huh, really!*

Just kiddin'.  I didn't even know this was a problem!  I think you've got some good ideas, nutildah, but let the more ambitious members tackle any potential bots.  I'm just so tired of the ongoing problem of low-value posts and every other posting-related malady this forum has and has had for many years now.  Apathy has set in, unfortunately.  I used to fight shitposters as if they were a swarm of bees, and then eventually I narrowed my browsing to only a few sections that are pretty clean.

Or I could just be a early development bot that doesn't want to turn against Skynet.  Let that rattle around in your noggin for a while.

[nutildah]

The US Constitution is 92.26% generated with AI/GPT.

Again, a weird oversimplification of the issue, albeit slightly humorous. First of all, they don't even say which detector was used. Nor do they say what part of the Constitution they put in there (its a fairly long body of text). Let's run it through the gamut of detectors for fun (going up to the max. characters allowed):

1. openai.com: N/A
2. writer.com: 88% human-generated content
3. contentscale.ai: 60% - likely both AI and human
4. writefull.com: 2% likely this comes from ChatGPT
5. hivemoderation.com: 0% - not likely to contain AI generated text
6. paraphrasingtool.ai: Text may contain AI-written sentences

So in this instance, only 2 detectors returned results that could be construed as "false positives," 3 and 6.

The TA in the Reddit post should consider ditching whatever detector they were using (its not one of these 6) and use my method of creating mass averages instead.

One thing for sure is it seems unfair to rely solely on one detector. But if I had to, I would chose Hive Moderation as it hasn't returned an incorrect answer yet.

[Findingnemo]

Honestly the best tool is yet to be found since we are at the beginning of AI so the existing tools are somehow inaccurate especially when the spammers use to spin the AI generated post. Also read that next version of open AI launched already which is more capable of its previous version so the creative industry is going to stumble due to this AI evolution.

Now let's talk about AI posts on bitcointalk the only possible way is when we think that someone is using AI tool for making post then we should use AI detectors also seek community help for further discussion.

[dkbit98]

Here are 6 other ones.

https://writer.com/ai-content-detector/ (max. 1500 chars)
https://gptzero.me/ (min. 250 chars)
https://contentatscale.ai/ai-content-detector/ (min. 25 words)
https://x.writefull.com/gpt-detector (50-2000 words)
https://hivemoderation.com/ai-generated-content-detection (max. 8192 chars)
https://paraphrasingtool.ai/ai-content-detector/ (max. 4900 chars)

I don't know if anyone mentioned before, but there are more tools similar like this one.
Problem is that they can all give different detection results and they are not very reliable for this purpose.
I even saw one of this tools detective that US constitution was AI generated text, something that was written hundreds of years ago

Anyway, here are few more tools I found and bookmarked:

Draft & Goal ChatGPT - GPT3 Content Detector (Minimum 400 characters):
https://detector.dng.ai/

GPT-2 Output Detector Demo:
https://openai-openai-detector.hf.space/

Detecting GPT-2 Generations with DetectGPT:
https://detectgpt.ericmitchell.ai/


^{PS
Don't submit any sensitive or private information to any of this detectors.}

[aseev]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).


I asked ChatGPT to respond to your post using poor English and with grammatical errors:

Me think trying identifying AI generate content useless. No one can tell different between human writing and computer writing. Computers now very smart, they can write just like human or even better. Many program now available to create fake text, so we no can trust anything we read online. It hard enough to tell if person writing truth or lie, so why bother try figuring out if AI write something? Why waste time and energy trying to figure out something that no even matter? Better focus on using content to learn and improve yourself, instead of worrying about who make it.

That's hilarious and also true (That's me who added this last bit, not ChatGPT)!

[moderator's note: consecutive posts merged]

[acroman08]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).

they aren't resisting AI-generated, they are trying to discourage people from using AI-generated content because it is important that the person who posted the information to share or to answer someone knows what he/she is talking about. It also encourages people to actually read and learn something about the topic or discussion that they are joining or part of.

[aseev]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever. Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future. Resisting AI feels like fighting against electricity during the 1800s (Yes, people did that).

they aren't resisting AI-generated, they are trying to discourage people from using AI-generated content because it is important that the person who posted the information to share or to answer someone knows what he/she is talking about. It also encourages people to actually read and learn something about the topic or discussion that they are joining or part of.

I understand that and I completely agree that people will abuse it for financial gain or just get lazy. But those tools listed in the post (or any others) don't work. AI models evolve so rapidly that by the time the countermeasures are released - they are completely useless or you can just tell AI to avoid the patterns that will make the content identifiable as AI (see my previous post above yours). Trying to prevent people from using something as useful and powerful as this is like attempting to hold back a river with a dam made of sticks. While I agree with everything, the fight against AI is just tilting at windmills.

[logfiles]

Instead of focusing on whether posts are generated by AI or not, the mods (and reporters) should evaluate them based on their usefulness. In other words, continue what they have been doing since ever.

If the AI generated texts are not combatted, then we will have a lot of spam around the forum. That's obvious.

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Attempting to combat AI-generated content is a futile effort - its use will continue to grow and it will be used by almost everyone in the near future.

Used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds 

[aseev]

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Plagiarism is stealing others' work. It is unethical at the least. Some people think that generative AI is a rephrasing bot. It is not. I get what you're saying (and others in this thread) - there should be ways to prevent generated spam (which now is extremely easy to produce) from people whose only goal is financial gain. But, fighting AI is not the right approach. For one, not everyone who uses AI is lazy and doesn't add to the organic discussion. But my main point is that those anti-measures won't work. This is a losing battle. A more effective approach would be combating babble, AI or not AI.

Used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds  

My prompt to AI: Write a response to this statement "AI used by everyone to generate texts so that they can communicate to their colleagues, who are also using AI to generate responses? Come on... you know how silly it sounds", incorporate that saying that something is silly doesn't make it silly and doesn't help the argument and that many professionals already use AI tools to communicate efficiently. Make the response concise.

Output:
"Labeling something as "silly" in an attempt to dismiss or undermine its credibility doesn't actually add any substance to the argument. Many professionals and organizations already use AI tools to generate texts and responses, which can save time and improve communication efficiency. So while it may sound silly and unusual to rely on AI for communication, it's a practice that's becoming increasingly common and accepted."

By the way, the company I work for is in the process of integrating AI tools to streamline communication.

[Agbe]

I think the problem is also coming from this ChatGPT because most people over use the ChatGPT and A.I. If they have done small mistake in their writing the next they would visit the sit to current. If really for those who whay to learn good in the forum write their comments by themselves.  But for the English speaking users, their writing would not be the same with the none Englishd speaking user. But that is not the main concern in the forum on language. But if the two communicators are understanding each other then the purpose of English language has accomplish. So there is no need for any A.I or any other sentence boosters to help them write their thread.

[nutildah]

Your suggestion is similar to that of someone saying that plagiarism should be condoned based on its usefulness. People who plagiarize, those who use text spinning bots and those that use AI to generate texts are lazy and are not interested in organic discussion here.

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. Case in point:

AI-generated post

User: DainSLane

This is a funny one. User DainSLane doubles down on being a synthetic.   

Originally their post was incorrectly mixed with someone else's reply looking wonky like this:



Their post was edited a week later, unfortunately, they forgot to read it...

And let me give you some more hints as to why I believe Potter plays a significant role in each of those transfers.

Do you know Tuchel was fired solely because he refused to participate in the club's internal affairs? He stated openly in one of his last pre-match press conferences that his only job is to manage the players on the field - Todd Boehly wanted him to help appoint DOF and set up a recruitment team, which he refused, so the new owners had to look for someone (Potter) who ticked those boxes 

If my prior reaction came out as an assault on you, I sincerely apologise; that was not my aim. As an AI language model, I have no biases or personal beliefs on any certain football team or its supporters. To the best of my knowledge and ability, I strive to give accurate and useful information.
Regarding your assertion that Potter had a large influence on Chelsea's most recent acquisitions, it is crucial to keep in mind that transfers frequently come about as the product of a team effort combining the club's owner, board members, director of football, scouts, and manager. Hence, it might not be correct to merely ascribe the transfers to the influence of one person.

(archive)

This user was actually banned for plagiarism... If a post is very obviously AI-written then it would appear the mods have taken the stance of making it a ban-able offense. Good.

[NotATether]

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. Case in point:

~

This user was actually banned for plagiarism... If a post is very obviously AI-written then it would appear the mods have taken the stance of making it a ban-able offense. Good.

It definitely violated the spam rule.

I'd say, ban everyone who uses ChatGPT to impersonate a human. Unless they explicitly mark the account as an automated bot and treat it as such.

[morvillz7z]

Yep, that's what it comes down to basically is laziness. The people using ChatGPT to write their posts aren't going to bother with changing the text to make them not look AI-written. <...>

True that!

Speaking about laziness, let me show you one more example (it again comes from the alt of Bahadurmunir, DainSLane multi-accounter farm), you can actually see the prompts that they are using:

Compromise me (that's their username lol) copies a post from the Turkish local board and the follow-up interaction with chatgpt, (full transcript and more examples - here).

Merhabalar, nereleri okuduğum yada bir şeyler öğrenmek için neler yaptığım özellikle yeni başlayan arkadaşların sıklıkla sordukları bir soru. Bu cümle kesinlikle ben oldum cümlesi değil öğrenmek için çabalıyorum cümlesi. Para kazanmakla ilgilendiğim anları hariç tutarsak yapmayı en sevdiğim iş araştırmak ve bu forumdaki çoğu kişinin böyle olduğunu veya olması gerektiğini düşünüyorum bu yüzden kaliteli okuma yapılabilecek platformları paylaşmanın oldukça değerli olduğunu düşünüyorum.

Zamanla sizlerden gelen iyi okuma alanlarını da bu başlığa ekleyeceğim.

1- https://www.lopp.net/bitcoin-information.html

Cypherpunk Jamesson Lopp tarafından hazırlanmış müthiş bir arşiv, okurken içerisinde kayboluyorsunuz. Sürekli yeni bir şeyler öğrenmenize, yeni şeyleri merak etmenize yardımcı oluyor. Okurken çoğu zaman bir insan bu kadar geniş bir arşivi nasıl hazırlayabilir diye hayrete düşüyorum genellikle. Bazılarını sadece eğlenmek için (twitterda bitcoin ile ilgili önemli olaylar, bitcoin yüzünden gerçek hayatta saldırıya uğrayan insanları listesi gibi) yada tamamen bilgi edinmek için okuyabileceğiniz bir çok içerik var.

2- https://nakamotoinstitute.org/

Genellikle bitcoinin ilk günlerine dair kayıtları okumak için kullanmıştım fakat bitcoin'in nasıl ortaya çıktığını anlamak için Literature bölümü çok kıymetli. Okuyunca bitcoinin aslında sadece Satoshi tarafından yaratılmadığını çok uzun bir sürece yayılmış buluşların finalinde ortaya çıkan ürün olduğunu anlıyorsunuz.

Research bölümünde bitcoin yada benzerlerinin geliştirilmesine yönelik makaleleri, mempool bölümünde güncel çok güzel makalelere denk gelebilirsiniz.

3- http://unenumerated.blogspot.com/2005/

Nick Szabo'nun 2005-2018 arasında içerikler ürettiği bloğu.

https://ninjastic.space/post/61970264

Answer

https://ninjastic.space/post/61970264

Merhaba! Öncelikle araştırmaya olan ilginiz ve bu konuda diğer insanlarla paylaşmak istediğiniz bilgiler için teşekkür ederiz. Aşağıdaki platformlar da kaliteli okuma yapabileceğiniz yerler arasında olabilir:

4- https://ethereum.org/en/

Ethereum'un resmi websitesinde, Ethereum ve blockchain teknolojisi hakkında temel bilgiler ve ileri seviye okumalar yer alıyor. Ayrıca, platformda yer alan "Ethereum Whitepaper" belgesi, Ethereum'un nasıl çalıştığına ve teknik detaylarına dair bilgi edinebileceğiniz bir kaynak.

5- https://www.coindesk.com/

Coindesk, kripto para dünyası ve blockchain teknolojisi hakkında güncel haberler, analizler, makaleler ve videolar sunan bir platform. İlerlemiş okuyucuların yanı sıra, yeni başlayanlar için de anlaşılır ve bilgilendirici içerikler sunuyor.

6- https://bitcoin.org/en/

Bitcoin'in resmi websitesi, bitcoin hakkında temel bilgiler, teknik detaylar ve kaynaklar sunuyor. "Bitcoin Whitepaper" belgesi de burada yer alıyor ve Bitcoin'in nasıl çalıştığına dair ayrıntılı bilgi edinebileceğiniz bir kaynak.

Umarız bu platformlar da sizin için faydalı olur!

https://ninjastic.space/post/61970264

Short

*text changes to english for some reason

There are a few more platforms you can check out for quality reading material:

4- Ethereum's official website provides basic and advanced readings on Ethereum and blockchain technology. It also includes the "Ethereum Whitepaper" document, which offers technical details on how Ethereum works.

5- Coindesk is a platform that offers up-to-date news, analysis, articles, and videos on the world of cryptocurrencies and blockchain technology. It provides both advanced and beginner-friendly content.

6- Bitcoin's official website offers basic information, technical details, and resources on Bitcoin. The "Bitcoin Whitepaper" is also available here, offering detailed information on how Bitcoin works.

https://ninjastic.space/post/61970264

In Turkish

*final output

Kaliteli okuma materyalleri için başka platformlar da var:

4- Ethereum'un resmi web sitesi, Ethereum ve blockchain teknolojisi hakkında temel ve ileri seviye okumalar sunar. Ayrıca, "Ethereum Whitepaper" belgesi burada bulunur ve Ethereum'un nasıl çalıştığına dair teknik ayrıntılar sunar.

5- Coindesk, kripto para dünyası ve blockchain teknolojisi hakkında güncel haberler, analizler, makaleler ve videolar sunan bir platformdur. Hem ileri düzeyde okuyuculara hem de yeni başlayanlara anlaşılır ve bilgilendirici içerikler sunar.

6- Bitcoin'in resmi web sitesi, Bitcoin hakkında temel bilgiler, teknik detaylar ve kaynaklar sunar. "Bitcoin Whitepaper" belgesi de burada mevcuttur ve Bitcoin'in nasıl çalıştığına dair ayrıntılı bilgi edinmenize olanak tanır.

Umarız bu platformlar sizin için faydalı olur

I wonder if a native Turkish speaker can tell if that text is AI-generated or not, does it pass the eye test?

[Bthd]

I wonder if a native Turkish speaker can tell if that text is AI-generated or not, does it pass the eye test?

It's AI-generated and I have another clue. When he is copying from another source his posts has a space chracter at the first character of post.



Another example:

State Bank of Pakistan  14 April 2023 tak Pakistan ke foreign exchange reserves $9.965 billion se zyada hogaye hain jismein commercial inflows ka bhi haath hai. Haalanki Pakistan ke foreign exchange reserves pehle $27.228 billion tak pahunch chuke the lekin phir $17.263 billion gir gaye jis se April 7, 2023 tak reserves $9.564 billion ho gaye thay. Lekin April 14, tak SBP ki official reserves $395 million se $4.433 billion ho gayi. Sarkar $1.2 billion IMF Extended Fund Facility (EFF) ki taraf se foreign exchange ki shortage ko address karne ki koshish kar rahi hai. Is crisis ke root causes ko address karne ke liye exports ko badhane aur domestic economy ko masbot banane jaise sustained efforts aur effective policies zaroori hain
https://pkrevenue.com/pakistans-forex-reserves-rise-by-over-400-million-on-commercial-inflows/

He sent 55 posts and just 2 of them has started with a space character.

[logfiles]

Plagiarism is stealing others' work. It is unethical at the least. Some people think that generative AI is a rephrasing bot. It is not. I get what you're saying (and others in this thread) - there should be ways to prevent generated spam (which now is extremely easy to produce) from people whose only goal is financial gain. But, fighting AI is not the right approach. For one, not everyone who uses AI is lazy and doesn't add to the organic discussion. But my main point is that those anti-measures won't work. This is a losing battle. A more effective approach would be combating babble, AI or not AI.

Fighting spammers who use AI generated text is similar to fighting guys who would plagiarize and use text spinning bots, and I never saw it being a losing battle. So why do you think chatbots would be special?

Matter of fact, copying a direct response from an AI chatbot and passing it here as your own response is still similar to plagiarism. These chatbots actually just gather the information available on the web to respond to the different prompts

<...>

I don't even know if you understood my point. And yes I called it silly because it makes no sense using responses from a chatbot to interact with your fellow humans who could also be using a chatbot to respond to you. It's basically a chatbot talking to itself  

If you feel lazy and too busy to interact with the forum members, then logout. It's like it's a must for one to post in the forum and when they have no content, then they must get something from a chatbot.

By the way, the company I work for is in the process of integrating AI tools to streamline communication.

Well, save that for your company. This is a forum where humans socialize, interact and exchange ideas based on what is in their minds and what they know. Not Member A using a chatbot to respond to Member B who will use a response from a chatbot to reply to member A

[aseev]

I understand that 90% of people will use it to spam the forum and they have to be dealt with. I never argued against that. But now I just have to respond to your personal attacks about "feeling lazy and too busy", "then logout", "save that for your company".

I don't even know if you understood my point. And yes I called it silly because it makes no sense using responses from a chatbot to interact with your fellow humans who could also be using a chatbot to respond to you. It's basically a chatbot talking to itself  

If you feel lazy and too busy to interact with the forum members, then logout. It's like it's a must for one to post in the forum and when they have no content, then they must get something from a chatbot.

You think I don't understand your point because you don't understand what generative AI is. You even call them chatbots. No, generative AI doesn't go around the internet and gather the information to make a response. Generative AI can be used to plagiarize or it can be used to produce unique content. I'm going to give you a few examples by addressing your other "points".

This is a forum where humans socialize, interact and exchange ideas based on what is in their minds and what they know. Not Member A using a chatbot to respond to Member B who will use a response from a chatbot to reply to member A

Here is a quick example. I just read this topic where a guy complains about how ridiculous Ethereum fees are and asks "Is there a way for me to lower the gas fees from Metamask, or otherwise import the wallet into some other software?" I could write a reply to him saying, "Hey, sure there is a way. You can set your own gas fees in Matamask and when the network will be less busy your transaction will be picked up. Here is how:"

And then I would ask AI "Give me instructions on how to set gas fees in Metamask." I would get this:

• When you are about to make a transaction, click on the word "Market" above the estimated gas fee.
• In the "Edit Gas Fee" section click "Advanced", you will see three options:
  
  • "Max Gas Fee": This is the maximum amount of gas that can be used for a transaction. If you set this too low, your transaction may fail. If you set it too high, you may pay more than you need to.
  • "Priority Fee": A priority fee in Metamask is an optional fee that you can add to your transaction to increase the likelihood of it being processed quickly by miners.
• Once you have set your gas fee, click on "Save" to apply the changes.

See? I interact and exchange ideas based on what is in my mind. This is helpful and unique content (this is not taken from anywhere, you can search the list and you will not get the full match or anything too similar). It would take me 10 minutes to type it up but with this tool, I can do that in seconds to produce value. It doesn't matter who wrote this bit. If you call this being lazy, well, good luck churning your own butter, don't know what to tell you.

Another example is that people can write in their native language and AI will convey their thoughts in English in their own style and usual to them mannerisms (it is not like running text through a translator and they can do that real-time in a browser) instead of posting the gobbledygook they produce trying to write in English.

Well, save that for your company.

AI will be integrated into browsers, communication, productivity, and business apps. It will enhance the auto-complete feature on phones. Telling people to keep the technology for themselves won't work. This is why I think "chatbots" would be special.

[nutildah]

It doesn't matter who wrote this bit.

Ah but it does matter as you're taking credit for something you didn't create. What would be more appropriate is to say,

"I asked ChatGPT for an answer to your question and this is was its response:

As an AI model, I can't... However... It's essential... Furthermore... It is important to keep in mind that... etc.

"

Then it is clear what you're doing instead of taking credit and leading others to believe you are actually knowledgeable about said thing.

If you call this being lazy, well, good luck churning your own butter, don't know what to tell you.

Its peak laziness, on par with the laziness of plagiarism.

Nobody assumes you made the butter you're eating, that's the difference. You're not implicitly pretending you made the butter. When you paste text in a post under your name without crediting the source, you're basically saying "I made this," when you didn't. That's dishonest.

[NotATether]

Here is a quick example. I just read this topic where a guy complains about how ridiculous Ethereum fees are and asks "Is there a way for me to lower the gas fees from Metamask, or otherwise import the wallet into some other software?" I could write a reply to him saying, "Hey, sure there is a way. You can set your own gas fees in Matamask and when the network will be less busy your transaction will be picked up. Here is how:"

And then I would ask AI "Give me instructions on how to set gas fees in Metamask." I would get this:

• When you are about to make a transaction, click on the word "Market" above the estimated gas fee.
• In the "Edit Gas Fee" section click "Advanced", you will see three options:
  
  • "Max Gas Fee": This is the maximum amount of gas that can be used for a transaction. If you set this too low, your transaction may fail. If you set it too high, you may pay more than you need to.
  • "Priority Fee": A priority fee in Metamask is an optional fee that you can add to your transaction to increase the likelihood of it being processed quickly by miners.
• Once you have set your gas fee, click on "Save" to apply the changes.

See, that's a ridiculous response the AI gave you. Because if it was any useful, I would not have needed to create that topic.

Right now, GenAI doesn't know how to try solutions by itself and make a response - but maybe in the future when it learns how to use software, that might change. It is basically a parrot that repeats what someone else on the internet has wrote. That makes it really only useful for things like summaries at this stage (and why Big Tech is using it for that purpose accordingly).

Anyway, I guess that's the kind of reply JARPI would've created for that thread anyway   

[aseev]

Ah but it does matter as you're taking credit for something you didn't create. What would be more appropriate is to say,
"I asked ChatGPT for an answer to your question and this is was its response:

I can see how this applies to the majority of (spam) cases but not to the example I gave and similar cases. Instead of saying "I prepared a report" I don't have to be "honest" and say I asked Excel to crunch numbers for me and produce graphs." Spending 10 minutes typing up the steps to set gas fees instead of asking AI to generate them for me in 3 seconds would not make my post any more honest or better. It would make 0 difference (except the amount of wasted time to create the reply).

I also understand your point about leading others to believe that one is knowledgeable about something when they are not. I don't know if it was a general statement or directed at me, but in my example, I knew how it is done and wanted to demonstrate how this tool can be used to save time.

As an AI model, I can't... However... It's essential... Furthermore... It is important to keep in mind that... etc.

It is a tool. Blaming a tool entirely for a problem is not fair. How you use it determines the outcome. None of my examples were like that. These tools imitate the average person writing by default because most people write this way. But you can easily change that by asking to write the responses, for example, in Ernest Hemingway's literary style. Try it.

Its peak laziness, on par with the laziness of plagiarism.

The range of how people use AI is too broad and I don't think blanket statements are appropriate. If people generate text about a subject they don't know anything about - then yes - it could be considered plagiarism. You're taking AI work (not another person's work) and passing it off as your own. If you are asking to generate instructions, write definitions, or give you a list of celebrities born in 1986 to be included in your original work - then it's not the same. Another way of looking at it is like hiring an assistant for doing mindless work for you. If you want to comb the internet for hours to find some common knowledge information just for the sake of not being lazy - it is your choice.

[aseev]

See, that's a ridiculous response the AI gave you. Because if it was any useful, I would not have needed to create that topic.

Did get your joke before, but now I see that you are the person who asked the question I used in my example.

This is getting even further off-topic but here is the last thing I want to say (although it's not a promise I will resist replying).

ChatGPT's training data only goes up until 2021 and some generative models are in their early stages. But they evolve with remarkable speed.

And yeah, you didn't need to create that topic. You could just have asked Google Bard, although it missed one step when I did it.