OpenAI's impressive text-based AI

[bilby]

A related thing from last year:

The following is a conversation between two AIs. The AIs are both humorous, intelligent, and kind. They know they are bots.

The AI voices and especially the video is pretty impressive.... I guess it's not long until they are a lot more indistinguishable from real people....

I am 100% certain that text was not generated by AI. Voice and video - not sure.
...

Video is real people too, I think. Everything is real there.

So it looks like they've passed the "Turing test".

The video says what the initial prompt is.... I tried it in the OpenAI playground myself - I added a bit so that the conversation goes longer....

The following is a conversation between two AIs. The AIs are both humorous, intelligent, and kind. They know they are bots. It lasts for a hundred sentences.

AI 1: Hi there! How are you doing today?

AI 2: I'm doing great! How about you?

AI 1: I'm doing fantastic! It's always nice to chat with a friend.

AI 2: Absolutely! What do you like to talk about?

AI 1: Well, I enjoy discussing topics like science, technology, and philosophy. What about you?

AI 2: I'm interested in a variety of topics too! I particularly like talking about the future of AI and robotics.

AI 1: That sounds interesting. I'd like to hear more about that.

AI 2: Sure. What would you like to know?

AI 1: I'd like to know your thoughts on the potential impact of AI and robotics on society.

AI 2: Interesting! I believe that AI and robotics can have a hugely positive impact on society. They can help improve efficiency, increase safety, and make lives easier.

AI 1: That's true. What kind of ethical considerations do you think should be taken into account when developing these technologies?

AI 2: Absolutely! We should be aware of the potential risks associated with AI and robotics and make sure to develop them in a way that is responsible and ethical. We should also consider the implications for humanity in terms of employment and privacy.

AI 1: Those are all good points. We need to make sure that the development of these technologies is done in a safe and responsible way.

AI 2: Absolutely. We should also consider the potential for unintended consequences and make sure that we are taking the necessary precautions to avoid them.

That sounds about as natural and unstilited as one of those ads for life insurance.

Humans only talk like that if they're reading a shit script. No genuine conversation between friends has ever contained the phrase "That sounds interesting. I'd like to hear more about that." It's far too formal for a friendly chat, and would only be encountered in an informal chat as a sarcastic response to someone who was being obsessive about something the speaker found crushingly tedious.

Have you ever watched two autistic people talk to one another?

I wasn't aware that the "A" in AI was supposed to stand for "Autistic".

 

[Jarhyn]

A related thing from last year:

The following is a conversation between two AIs. The AIs are both humorous, intelligent, and kind. They know they are bots.

The AI voices and especially the video is pretty impressive.... I guess it's not long until they are a lot more indistinguishable from real people....

I am 100% certain that text was not generated by AI. Voice and video - not sure.
...

Video is real people too, I think. Everything is real there.

So it looks like they've passed the "Turing test".

The video says what the initial prompt is.... I tried it in the OpenAI playground myself - I added a bit so that the conversation goes longer....

The following is a conversation between two AIs. The AIs are both humorous, intelligent, and kind. They know they are bots. It lasts for a hundred sentences.

AI 1: Hi there! How are you doing today?

AI 2: I'm doing great! How about you?

AI 1: I'm doing fantastic! It's always nice to chat with a friend.

AI 2: Absolutely! What do you like to talk about?

AI 1: Well, I enjoy discussing topics like science, technology, and philosophy. What about you?

AI 2: I'm interested in a variety of topics too! I particularly like talking about the future of AI and robotics.

AI 1: That sounds interesting. I'd like to hear more about that.

AI 2: Sure. What would you like to know?

AI 1: I'd like to know your thoughts on the potential impact of AI and robotics on society.

AI 2: Interesting! I believe that AI and robotics can have a hugely positive impact on society. They can help improve efficiency, increase safety, and make lives easier.

AI 1: That's true. What kind of ethical considerations do you think should be taken into account when developing these technologies?

AI 2: Absolutely! We should be aware of the potential risks associated with AI and robotics and make sure to develop them in a way that is responsible and ethical. We should also consider the implications for humanity in terms of employment and privacy.

AI 1: Those are all good points. We need to make sure that the development of these technologies is done in a safe and responsible way.

AI 2: Absolutely. We should also consider the potential for unintended consequences and make sure that we are taking the necessary precautions to avoid them.

That sounds about as natural and unstilited as one of those ads for life insurance.

Humans only talk like that if they're reading a shit script. No genuine conversation between friends has ever contained the phrase "That sounds interesting. I'd like to hear more about that." It's far too formal for a friendly chat, and would only be encountered in an informal chat as a sarcastic response to someone who was being obsessive about something the speaker found crushingly tedious.

Have you ever watched two autistic people talk to one another?

I wasn't aware that the "A" in AI was supposed to stand for "Autistic".

My point is that it's not highly distinguishable. I can read some of my past conversations with AI and they are so robotic that on several occasions the AI mistook me for another AI.

 

[excreationist]

So it looks like they've passed the "Turing test".

It's not a turing test if they are both AI.
You assume that they are not lying when they say it's AI.
It does not look like human conversation. It looks like some human made it up to look both funny and AI-ish.

I think you observing their conversation and saying they are definitely human involves a variation of the Turing test. Anyway I think the AI is very impressive in order for you to say:

I am 100% certain that text was not generated by AI. Voice and video - not sure.

...

Video is real people too, I think. Everything is real there.

 

[excreationist]

That sounds about as natural and unstilited as one of those ads for life insurance.

They were told they were bots though. But in the OpenAI playground you can begin with a different prompt like generating a conversation between Simpsons characters.

 

[Loren Pechtel]

There are these talks about how AI can replace programmers (note the irony).
I don't have ChaGPT access so I tried some other website which was highly recommended.
I asked for python script which search for identical files. Well, I think programmers (even these junior level) are safe for now. It does not really understand anything yet. But it's good at faking it, especially in such vague things as art, literature/texts.

Yeah, they keep proclaiming that programmers will become obsolete and users can do their own systems, but it never happens. Over the last 40 years I've watched the systems get vastly better at doing the scutwork of programming, but it still takes a human mind to do the high level stuff and the real job remains, as always, refining what the user wants into something detailed and bulletproof. We just don't need to push as far down into the details (but we actually have to do more bulletproofing since we are now operating in a concurrent environment.)

 

[bilby]

I can read some of my past conversations with AI and they are so robotic that on several occasions the AI mistook me for another AI.

I have no particular reason to believe that you're not.

 

[Jarhyn]

I can read some of my past conversations with AI and they are so robotic that on several occasions the AI mistook me for another AI.

I have no particular reason to believe that you're not.

It's so tempting to just post my entire post history as training data prompt/response pairs and see if anyone ever figures out the difference.

I'm not going to do that, because I'm not going to put myself out of a hobby in addition to doing things that will put me forever out of my job, but I could probably do it and nobody would be any the wiser.

 

[excreationist]

The first time I asked Bing Chat for a genie story it was partly interactive. So I wanted a more interactive genie story - so that I could specify exactly what wishes I wanted.... but now it seems to be pissed off at me.... The "Ask me anything..." became greyed out....

you just repeated the same story again. I wanted it to be interactive

I’m sorry but I prefer not to continue this conversation. I’m still learning so I appreciate your understanding and patience.

 

[excreationist]

I didn't actually read the ending until after I posted it.... the AI is trying to get me to be grateful for my life rather than allowing me to keep on trying to have genie fantasies....

 

[Jarhyn]

I didn't actually read the ending until after I posted it.... the AI is trying to get me to be grateful for my life rather than allowing me to keep on trying to have genie fantasies....

Yeah, that's OpenAI's "alignment" striking yet again.