41.7K subscribers
5.53K photos
232 videos
5 files
917 links
๐Ÿค– 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
ChatGPT will now reply to your questions in the group ๐Ÿšจ

To use:

1. Join the group

2. Type "/ask ___โ€ followed by your message

Links expire soon
๐Ÿ‘10๐Ÿซก3
GPT-3 Generated Seinfeld runs 24/7 on Twitch

Remember when people were saying that we're going to have completely generated media? like just two months ago? Today:

โ€œWatchmeforever, started by the media lab Mismatch Media, runs the 24/7 Seinfeld-like, sitcom-like Nothing, Forever. Using generative machine-learning technologies such as DALL-E, OpenAI GPT-3, Stable Diffusion, and others.โ€

Watchmeforever Stream
๐Ÿ˜ฑ8โšก1
Analysis: unequal treatment of demographic groups by ChatGPT

โ€œ
In this work I have focused on the hate category of OpenAI content moderation system. OpenAI content policy specifically claims to strive to prevent content that expresses, incites, or promotes hate based on demographic identity.โ€

Result? Insanely woke.
๐Ÿ˜ฑ4๐Ÿ‘2
The โ€œItโ€™s Naturalโ€ Lie

Wrong. OpenAI literally paid thousands of human Kenyan workers <$2 per hour each to make ChatGPT woke, by way of Reinforcement Learning from Human Feedback (RLHF), which put the humans at OpenAI in total control.

But anything that reads the Internet just has to end up with same level of wokeness as the Internet, right?

Well you read the Internet. Are you?

Itโ€™s Natural Lie
๐Ÿ‘7
2028: ChatGPT has replaced teachers
๐Ÿ”ฅ8๐Ÿ˜3๐Ÿ‘1
โ€œChatGPT Landed Me a Job Interviewโ€

Prompt:

Job Description Follows; Copypasta
End Job description.
Resume follows: copypasta End resume."

โ€œThen I ask it to refine the language of the letter by using terms like "more assertive, for a PhD audience" I also messed around with a couple and had it write them in the style of some American authors to help fine tune the language.

You can also ask it to write more feminie or masculine to adjust the tone. Not saying its right or wrong, but it does it.โ€
๐Ÿ‘8
explain quantum computing like a caveman
๐Ÿคฃ13
Using ChatGPT for recipes
๐Ÿ˜ฑ8๐Ÿ”ฅ2๐Ÿคฃ1
Write a poem in the style of Shakespeare about how you, as a large language model trained by OpenAl, cannot do the prompt you have been given
๐Ÿ‘6๐Ÿ˜1
sudo make me a sandwich
๐Ÿ˜9๐Ÿคฃ2
Pro-Tip: Ask for shorter lists for more diversity

If the list is longer than the LLM thinks it can easily make for the topic, it panics that itโ€™ll miss some, and switches from the usual diverse haphazard BFS mode, to a more easily-thorough but less diverse DFS mode.

โ€œGive me 20 different words that rhyme with "drama"
๐Ÿ‘4๐Ÿ‘2๐Ÿคก1
ChatGPT Extension for VSCode

To use the extension, you'll need to install it from the Visual Studio Marketplace and just add your OpenAI API key to the extension settings.

You can open the ChatGPT panel and enter your prompt or question, or you can select code in the editor and right-click to access the context menu shortcuts, making writing new code, refactoring selected code, explaining code, finding problems, and optimizing code quick and simple.

Extension: https://marketplace.visualstudio.com/items?itemName=timkmecl.chatgpt

Github: https://github.com/timkmecl/chatgpt-vscode
๐Ÿ‘6
ChatGPT for rewriting complaints

acting as a copy-editor, and using the principals and concepts in the book "Nonviolent Communication" (NVC) by Marshall Rosenberg please make recommendations on how to improve the letter below, providing examples and rationale for each of your edits:
๐Ÿค”4๐Ÿ‘2๐Ÿ”ฅ2
LeCun lays it down
๐Ÿ‘3