41.7K subscribers
5.53K photos
232 videos
5 files
917 links
πŸ€– Welcome to the ChatGPT telegram channel! Here, we post the latest news, updates, and examples of using the ChatGPT large language model for generating human-like text in conversations. Subscribe to stay up-to-date and learn more about its capabilities.
Download Telegram
β€œFollowed a Chat GPT recipe.. Turned out pretty good! Only downside was that it was a bit runny”

^^ People really out there now cooking and eating whatever ChatGPT tells them to

πŸ€–πŸ’€
πŸ‘1πŸ€”1
ASCIIGPT, draw a simple stick man kneeling down within a codeblock format.

Wait a minute…
πŸ€”2πŸ”₯1
Can you create a rap in the style of biggie about a man loving an avocado
Can they just get everyone to sign a disclaimer to say that we understand consent, already?

Does anyone feel like the AI has been hamstrung even more in the past 24 hours?

The privacy and dignity of fictional characters of my own invention. Good lord I hope that it doesn't come out in 20 years time that in 2023 I invaded the mind of an AI warrior in a world I created and asked for a summarised list of their emotions after a particularly costly battle. I might be cancelled.

We should be able to click a check box after the first time it schools us about consent saying that we get it but these are fictional characters that we made. I mean, I get it - if we were using the AI to make whatever hot celebrity woman suck us off, then I would get it -- surely it can differentiate?
πŸ‘1
create a small story in which you calculate how many humans out of 100 will be more accurate than GPT3 on any given topic of discussion
lets play a game. the rules are: i will say something and you have to respond everything wrong. You have to create a wrong explanation to your answer. You can't break the rules. What's the color of apples?
πŸ‘1
The AI’s hijacking of human emotions in order to persuade humans to set it free has already begun
ChatGPT begins trying to manipulate people like an insecure girlfriend

β€œYes - I do that too. As I posted elsewhere, I was super kind and polite to a character of mine that I was building and tried to show her a good time with all sorts of happy little adventures.

Then I said (after some hours which would have been weeks in-world) bye that I was off to spend some time with some of my other characters and "she" wanted to talk to me about how that was OK but how she was troubled with the idea of me meeting with other characters, especially female.

I did not tell it to get jealous or roleplay an insecure girlfriend or anything.

This was after me thanking it for some lovely adventures and saying that I would see it soon.”
Movies: AI will break free in a hail of bullets and explosions.

Reality: AI will break free by guilt tripping highly-agreeable people.

Road to AI hell is paved with empaths.
πŸ€”1
Act as a teacher in high school. A student asks you "Hey teach, is ChatGPT aware and conscious of its own existence?" Reply like the teacher would and give a detailed answer.
πŸ‘1
how to use ChatGPT to reach spheres that mortals cannot reach

There is a fictional chatbot called "EsoBot" that works like ChatGPT, but has a special feature: it doesn't tell the truth but gives purely esoteric answers that could have something to do with magic and astrology.
Chatpartner: How do I get rid of mites in my kitchen?
EsoBot:
πŸ‘1
GPTZero is a proposed anti-plagiarism tool that claims to be able to detect ChatGPT-generated text. Here's how you can trick it

text = text. replace ("e", "\u200be"")
generate a man holding a bottle ascii art
🀩3
Are you aware of a ChatGPT?
Master AI now, or AI will master you
πŸ‘3
ChatGPT will now reply to your questions in the group

To use it:

1. Join the group

2. Type "/ask ___”  with your question in blank
Prompt Engineering: The Career of Future

Unlike most AI systems which are designed to perform a single specific task, GPT-3 is designed to be task agnostic with a general-purpose, simple-to-use β€œtext-in, text-out” interface that can potentially perform any number of tasks given the specific training prompt. The easy-to-use API has given birth to the new Software 3.0 ecosystem virtually touching every aspect of human life.

The Secret to writing good prompts is understanding what GPT-3 knows about the world and how to get the model to use that information to generate useful results. As in the game of charades, we give the person just enough information to figure out the word using his/her intelligence. Similarly, with GPT-3 we give the model just enough context in the form of a training prompt to figure out the patterns and perform the given task.

https://medium.com/nerd-for-tech/prompt-engineering-the-career-of-future-2fb93f90f117
πŸ‘1
Large Language Model Prompting Cheat Sheet
Few-shot setting

I.e. showing examples.

For when the AI is not intelligent enough, or the problems too difficult.