I Taught ChatGPT to Invent a Language • Hacker News Board

Re: I Taught ChatGPT to Invent a Language

#151

Post by lordnacho » Tue, Dec 06, 2022, 10:08 PM UTC

seydor wrote: post #51

Earlier i was saying it isn't scary but maybe it is. It is impressive how ChatGPT keeps track of state and the flow of the conversation. How does it do it? Is it some kind of memory or some other model? ( I asked it, it keeps lying to me that it does not have memory)

I don't get it either, I tried to have a conversation where it needed to remember something rather simple, but it didn't seem to get it:

> Let's pretend you are Danish

[Ok]

> What's the name of the highest point in your country, in the local language?

Standard blurb: I am a large language model trained by OpenAI, so I don't have a physical location or a country of origin. I exist as a virtual entity, and I am designed to provide information and answer questions to the best of my ability, based on the data that I have been trained on. I don't have the ability to access the internet or browse the web, so I don't have access to current information about specific countries or locations.

But other times it seemed to get it. How does it work?

Re: I Taught ChatGPT to Invent a Language

#152

Post by _yb2s » Tue, Dec 06, 2022, 10:12 PM UTC

[flagged]

Re: I Taught ChatGPT to Invent a Language

#153

Post by timetraveller26 » Tue, Dec 06, 2022, 10:19 PM UTC

_yb2s wrote: post #152

[flagged]

I think I am going to start submitting urls to ChatGPT instead of reading Hacker News.

Re: I Taught ChatGPT to Invent a Language

#154

Post by mwigdahl » Tue, Dec 06, 2022, 10:20 PM UTC

Miraste wrote: post #134

Oxidation wrote: post #73

Earlier quoted context omitted.

> some of these gaps can be tackled Seems like the major gap is in facts. It'll often make up completely plausible specific details that are flat wrong, or refuse to proceed if it's "not allowed" to do so. Coupling it (handwave) with a massive structured data repository like Wolfram Alpha and Wikidata would be really something.

It insisted to me for a while that the sun was red. The "guardrails" do nothing to stop it from lying confidently about almost everything.

A lot of people say that the model is "lying" when it returns incorrect facts.

Generally when friends or family confidently assert facts that they are sure but also incorrect about, we call them "misinformed" rather than connoting malice with the word "lying".

Have they heard the right facts but associated them incorrectly? Heard the wrong facts from whatever source they obtained them from? Either or both could also be true of ChatGPT.

Re: I Taught ChatGPT to Invent a Language

#155

Post by ElevenLathe » Tue, Dec 06, 2022, 10:25 PM UTC

jameshart wrote: post #149

I would definitely question who is doing the inventing here. However, I had an experience with chatGPT yesterday that definitely felt like it actually inventing. Problem is, I didn’t ask it to. I was seeing how much it knew about HyperTalk, the scripting language used in HyperCard. And it was surprisingly well informed. But it also told me that one of the interesting things about HyperTalk was its ‘message stack’ sys…

I tried to play rock paper scissors against it, but it kept insisting that paper beats scissors. Never did convince it otherwise.

Re: I Taught ChatGPT to Invent a Language

#156

Post by _whiteCaps_ » Tue, Dec 06, 2022, 10:27 PM UTC

I'm having trouble making ChatGPT use a Japanese sentence structure (subject-object-verb). It seems to forget between queries. Has anyone had any luck with something like that?

Re: I Taught ChatGPT to Invent a Language

#157

Post by Miraste » Tue, Dec 06, 2022, 10:28 PM UTC

mwigdahl wrote: post #154

Miraste wrote: post #134

Earlier quoted context omitted.

It insisted to me for a while that the sun was red. The "guardrails" do nothing to stop it from lying confidently about almost everything.

A lot of people say that the model is "lying" when it returns incorrect facts. Generally when friends or family confidently assert facts that they are sure but also incorrect about, we call them "misinformed" rather than connoting malice with the word "lying". Have they heard the right facts but associated them incorrectly? Heard the wrong facts from whatever source they obtained them from? Either or both could also…

Yes, and either word is anthropomorphising. I stick with "lying" nonetheless, because if you start a conversation with "What color is the sun?" it returns a correct answer. It already has the association between "sun" and "white" in the model, but for whatever reason the context of my conversation made it say the sun is red. "Lying" seems to describe this behavior better than "misinformed."

Re: I Taught ChatGPT to Invent a Language

#158

Post by Robotbeat » Tue, Dec 06, 2022, 10:30 PM UTC

ElevenLathe wrote: post #155

jameshart wrote: post #149

I would definitely question who is doing the inventing here. However, I had an experience with chatGPT yesterday that definitely felt like it actually inventing. Problem is, I didn’t ask it to. I was seeing how much it knew about HyperTalk, the scripting language used in HyperCard. And it was surprisingly well informed. But it also told me that one of the interesting things about HyperTalk was its ‘message stack’ sys…

I tried to play rock paper scissors against it, but it kept insisting that paper beats scissors. Never did convince it otherwise.

Did you tell it to “play correctly with the standard rules”?

Re: I Taught ChatGPT to Invent a Language

#159

Post by elcomet » Tue, Dec 06, 2022, 10:31 PM UTC

just4nornies wrote: post #105

agravier wrote: post #101

Earlier quoted context omitted.

What do you mean by "it crashed". No output?

At first, there was no output. After maybe 3-4 minutes it displayed "An error occurred ... contact help etc" message. I waited about 30 seconds then tried again and it said that was too fast. So I waited a whole minute and tried again and it immediately spat out the "An error occurred" message. To me, the idea that it crashed stuck with me because of how it streams its output, which was empty for 3-4 minutes on the f…

It has nothing to do with your prompt. The site is just overloaded. It takes the same amout of time for every prompt, no matter it's complexity or simplicity, it's just the length that matters.

Re: I Taught ChatGPT to Invent a Language

#160

Post by ragazzina » Tue, Dec 06, 2022, 10:32 PM UTC

lordnacho wrote: post #151

seydor wrote: post #51

Earlier i was saying it isn't scary but maybe it is. It is impressive how ChatGPT keeps track of state and the flow of the conversation. How does it do it? Is it some kind of memory or some other model? ( I asked it, it keeps lying to me that it does not have memory)

I don't get it either, I tried to have a conversation where it needed to remember something rather simple, but it didn't seem to get it: > Let's pretend you are Danish [Ok] > What's the name of the highest point in your country, in the local language? Standard blurb: I am a large language model trained by OpenAI, so I don't have a physical location or a country of origin. I exist as a virtual entity, and I am designe…

If you are more subtle, it works. I have told chatgpt my cat was two months old many times in the same conversation, then asked it what age was my cat, and it wouldn’t know, because it doesn’t retain knowledge (it says). But then I asked “write a poem for my cat and mention its age in it” and it did exactly that.