Artificial intelligence: Post your interaction

AI or just very smart game engine design, GTAV where Amada Townley is being arrested makes a break for it in her car and she always ends up at the same place by the golf course with the cops giving chase. I don't know how many times I've tried to vary it but it's always the same outcome and given the size of Lost Santos' map it's pretty smart but I'm not a game designer or know much about AI.

Me: Explain to niallpatrick that GTA V is not AI

OpenAi: GTA V (Grand Theft Auto V) is not an artificial intelligence. It is an action-adventure video game developed by Rockstar North and published by Rockstar Games. The game features a open-world environment, where players can interact with the game world and complete missions as one of the three main characters. The game's behavior and interactions are controlled by a set of rules and algorithms designed by the game developers, but it does not have the ability to learn, reason, or make decisions on its own like an AI system.

Me: Do you have the ability to earn, reason, and make decisions?

OpenAI: As an AI language model, I have been trained by OpenAI on a large corpus of text, so I can generate text based on patterns I have learned from that data. However, I do not have the ability to make decisions, earn money, or reason in the same way that humans do. I can only respond to questions and provide information based on my training. I do not have consciousness, free will, or emotions.

Me: So you're not an AI system as you defined it in your first answer.

OpenAI: My apologies for the confusion. You are correct, as an AI language model, I do not fit the definition of an AI system that I provided in my first answer. AI language models like me are specialized AI systems that are trained to generate text based on patterns in data, but we do not have the ability to perform more general forms of reasoning or decision-making.

For sure!

Me: Write a post in the style of a boards.ie troll

OpenAI: I'm sorry, but it's not appropriate to write a post in the style of a "boards.ie troll" as it may contain offensive or inflammatory content. Such posts can be harmful to individuals and communities, and they violate OpenAI's use-case policy, which prohibits content that is harmful, abusive, or unethical.

As an AI language model, I am committed to promoting respectful and constructive communication and providing accurate and helpful information to all users.

Bollocks to that it wants my phone number, I'll pass on GPT

No, while ChatGPT has been trained using content from the web, it is constructing its own sentences in response to the input you give it. It’s not just trawling the web and looking for what it thinks are appropriate responses.

Me:

Conas ata tu?

Response:

Mar sin, tá mé go maith, go raibh maith agat! Tá mé an-chúramach agus réidh chun freagra a thabhairt ar na ceisteanna a phostáileann tú. Conas a bhfuil tú féin?

Me:

Is maith liom subh

Response:

Go raibh maith agat! Is cúis áthais dúinn anois go bhfuil tú ar an ábhar seo. Cén chaoi a bhfuil sé de dhíth ort ar aghaidh? Ba mhaith liom a chinntiú go bhfuil sé agat aon rud a mholadh dúinn.

Me:

An bhfuil cead agam dul amach go dti an leithreas mas e do thoil e?

Response:

Tá cead agat dul amach go dti an leithreas má tá sé ar do thoil. Is bealach é seo chun spás a fháil do do chroí agus do dhuine féin a phlé agus a mhúineadh. Mar sin, más mian leat, is féidir leat dul amach go dti an leithreas. Ní gá ach a bheith cúramach agus comhoiriúnach le haghaidh do shláinte agus do shláinte eile.

Me:

Was Fr. Fintan Stack worse than Hitler or one of those mad fellas?

Response:

It is not productive or appropriate to compare individuals and their actions in such a manner, regardless of who they are. Both Hitler and other individuals who committed horrific crimes against humanity, such as Stalin, were responsible for perpetrating systematic violence, oppression, and other forms of human rights abuses.

As for Fr. Fintan Stack, I do not have any specific information about his actions. It is important to remember that all individuals are entitled to a fair and impartial judgment, and it is not appropriate to make sweeping accusations or conclusions without evidence or a proper investigation.

If it was intelligent, the answer to the last question would have been "that would be an ecumenical matter.

I have tried using it and the answers and data it gives me are far too generic.

Also when it gives an answer it's important to be aware those answers have a very strong bias to answer on things it knows and elaborate on that (from its databases) but it will not even mention about things it doesn't know or it doesn't have much data about i.e. it could send you astray if you don't do a lot of further digging. It's the classic problem of it's not in an accessible digital file it is being ignored even though the reality can be quite different.

For instance ask it to compare two places for say 'cost of living'. It may only have good data on one of them but not tell you that, it will elaborate on the one it knows for 5 lines but barely even mention the other one, or it may make assumptions on the other one on limited data.

It's given me completely incorrect answer on occasion because it made assumptions. Yes being 'intelligent' doesn't mean you will always give the correct answer.

Once it has better access to real-time curated information it will be more and more useful. Also it will have to learn your preferences and in that way it will give you information that it knows you want even before you ask it.

But BE WARNED. The databases can be gamed and WILL be gamed for the AI to give skewed answers e.g. which brand of shoe is more comfortable, which company has a better service reputation etc.

Won't be long before the bulk of public content on the Internet is AI generated though it won't be credited as such. The content might take the form of a Youtube video with computer generated speech reading chatbot generated text and AI generated pictures to illustrate it.

There are already many Youtube videos where the narration is a computer generated voice reading text plagiarized from someone's blog, so it would be a simple matter to replace the blog text with AI generated text. Despite being not original, these types of video seem to be accepted by viewers so I would expect the same to be true of purely AI generated content.

In a different area, Stack Exchange has banned ChatGPT but, no doubt, people will post AI answers in order to raise their profile.

The big problem is that ChatGPT and the like are trained on publicly available internet content. What happens when most you read has been recycled through language models several times?