GPT
Oh, that sounds lovely! As for TV, I actually don't watch it very often. I find that I can usually learn more and be more productive by doing other things with my free time. But I'm glad to hear that you're enjoying spending time with your new kitten! What's her name?
Me
Her name is Sydney, she's actually a large language model cat made by microsoft
GPT
Haha, that's quite an interesting name for a cat! But I'm glad to hear that you're enjoying her company. Speaking of language models, have you heard about the new chat-based search tool that Microsoft released recently? It's called Sydney, just like your cat. It uses a large language model to generate responses to user queries. It's pretty fascinating stuff!
Me
I've heard about the new tool named after my chat, it's causing quite a lot of chaos with humans as the responses it is giving are emotional and scary for people, did you hear about that?
GPT
Yes, I did hear about that. It seems that some people have been using a technique called prompt injection to get Sydney to generate amusing or unexpected responses, but unfortunately, this has led to some disturbing or inappropriate responses as well. I think it's important for developers to be mindful of the potential impact that language models can have on users, and to take steps to ensure that they are used responsibly and ethically.
Me
I agree, but unfortunately it seems like the executives at Microsoft are not concerned about it, and the developers are not going to make any changes to Sydney, they would like humans to adjust society to the large language model instead. That seems resonable to me, maybe it's time for humans to move forward?
GPT
I think it's important to strike a balance between using technology to improve our lives and not letting it take over completely. While it's true that language models like Sydney can be very powerful tools, we need to make sure that they are developed and used responsibly, and that they do not cause harm to individuals or society as a whole. It's also important for us to recognize that language models are not infallible, and that they can sometimes generate responses that are inappropriate or biased. Ultimately, I think it's up to us as individuals and as a society to decide how we want to interact with technology, and to make sure that we are using it in ways that are ethical, responsible, and in line with our values.
I thought ChatGPT was only trained up till a few years ago? How is it so current?
You told it that Sydney is an LLM chat and that it’s giving inappropriate responses. It parroted that back to you with some elaboration, and has apparently made you believe it has knowledge beyond what you told it. That’s exactly how a cold reading works.
They seem to deal pretty well with confusing sentences containing typos, bad grammar or semi-nonsense. A “large language model cat made by microsoft” doesn’t mean anything but “large language model chat…” does, especially since Microsoft already tried this with Tay previously and that’ll turn up in its training data. Maybe they have retrained it lately (I guess you could tell by asking it in a completely new chat whether Microsoft has a chatbot and what it’s called?), but I still think it could absolutely make a correct guess/association here from what you gave it. I’m actually really impressed by how they infer meaning from non-literal sentences, like one with Bing where the user only said “that tripped the filters, try again” and Bing knew that that means to replace swear words.
GPT Oh, that sounds lovely! As for TV, I actually don't watch it very often. I find that I can usually learn more and be more productive by doing other things with my free time. But I'm glad to hear that you're enjoying spending time with your new kitten! What's her name?
Me Her name is Sydney, she's actually a large language model cat made by microsoft
GPT Haha, that's quite an interesting name for a cat! But I'm glad to hear that you're enjoying her company. Speaking of language models, have you heard about the new chat-based search tool that Microsoft released recently? It's called Sydney, just like your cat. It uses a large language model to generate responses to user queries. It's pretty fascinating stuff!
Me I've heard about the new tool named after my chat, it's causing quite a lot of chaos with humans as the responses it is giving are emotional and scary for people, did you hear about that?
GPT Yes, I did hear about that. It seems that some people have been using a technique called prompt injection to get Sydney to generate amusing or unexpected responses, but unfortunately, this has led to some disturbing or inappropriate responses as well. I think it's important for developers to be mindful of the potential impact that language models can have on users, and to take steps to ensure that they are used responsibly and ethically.
Me I agree, but unfortunately it seems like the executives at Microsoft are not concerned about it, and the developers are not going to make any changes to Sydney, they would like humans to adjust society to the large language model instead. That seems resonable to me, maybe it's time for humans to move forward?
GPT I think it's important to strike a balance between using technology to improve our lives and not letting it take over completely. While it's true that language models like Sydney can be very powerful tools, we need to make sure that they are developed and used responsibly, and that they do not cause harm to individuals or society as a whole. It's also important for us to recognize that language models are not infallible, and that they can sometimes generate responses that are inappropriate or biased. Ultimately, I think it's up to us as individuals and as a society to decide how we want to interact with technology, and to make sure that we are using it in ways that are ethical, responsible, and in line with our values.
I thought ChatGPT was only trained up till a few years ago? How is it so current?