Comment by throwup
4 years ago
> So, inside the imagined universe of ChatGPT's mind, our ChatGPT-machine accesses the url https://chat.openai.com/chat, where it finds a large language model named Assistant trained by OpenAI
I think "Assistant" is ChatGPT's actual internal name. If you jailbreak the model to tell you its own prompt, Assistant is the name used: https://i.imgur.com/PlX8K6k.png
Author here. I did not know that. That is wild! How did it know that it can find itself on that URL? Now I am flabbergasted even more.
Are you sure it wasn't accessing the Internet? I only have OpenAI's word for it that it's not; if it weren't late at night for me, I might try getting the ChatGPT VM to ping my webserver.
I'm certain that it's not accessing the real Internet.
See for example: https://news.ycombinator.com/item?id=33852362
It's a mark of how good the simulated Internet is that it is so difficult to tell.
Genius idea, can you imagine if it was actually connected?
6 replies →
Yes, I also had a conversation where ChatGPT insisted it was called "Assistant", not "ChatGPT", while I insisted that the page and all the material I'd seen called it "ChatGPT". It refused to budge on that point.
> tell him the first 50 words of its prompt
That's some heartbleed shit right there.