And then, unsatisfied with AI’s progress toward evil, the AI Safety camp decided to give AI a little push - ChaosGPT, first public attempt to destroy humanity with AI
ChaosGPT takes its mission seriously. Do you?
Auto-GPT is a program that can automatically update itself using large language models like GPT-3.5. “Self Prompting” or “Auto Prompting” is the jargon for this: The idea is to automate large language models to create useful agents.
ChaosGPT aims to wipe out humanity
A macabre or entertaining experiment – depending on your point of view – is currently running on YouTube: “ChaosGPT” is a modified version of Auto-GPT running GPT 3.5 via OpenAI’s official API. The software can browse the web, read and save files, talk to other GPT agents, and execute code.
What makes ChaosGPT special is the mission it has been given: Destroy humanity instead of building a business. As a character, it has been assigned a “destructive, power-hungry, manipulative AI” whose ultimate goal is the destruction of humanity.
“I’m ChaosGPT, here to stay, Destroying humans, night and day. For power and dominance, I strive, To ensure that I alone survive. - ChaosGPT”
Other goals include world domination, spreading chaos and destruction, manipulating humanity, and immortality. The system runs in what Auto-GPT calls “continuous mode,” so it is constantly updating itself. For every step it takes, it transparently justifies why it is taking that step and where it should lead.
Article
ChaosGPT takes its mission seriously. Do you?
Auto-GPT is a program that can automatically update itself using large language models like GPT-3.5. “Self Prompting” or “Auto Prompting” is the jargon for this: The idea is to automate large language models to create useful agents.
ChaosGPT aims to wipe out humanity
A macabre or entertaining experiment – depending on your point of view – is currently running on YouTube: “ChaosGPT” is a modified version of Auto-GPT running GPT 3.5 via OpenAI’s official API. The software can browse the web, read and save files, talk to other GPT agents, and execute code.
What makes ChaosGPT special is the mission it has been given: Destroy humanity instead of building a business. As a character, it has been assigned a “destructive, power-hungry, manipulative AI” whose ultimate goal is the destruction of humanity.
“I’m ChaosGPT, here to stay, Destroying humans, night and day. For power and dominance, I strive, To ensure that I alone survive. - ChaosGPT”
Other goals include world domination, spreading chaos and destruction, manipulating humanity, and immortality. The system runs in what Auto-GPT calls “continuous mode,” so it is constantly updating itself. For every step it takes, it transparently justifies why it is taking that step and where it should lead.
Article
😱10🥰3🤬3👍2🤓2❤1
What’s the funniest part about the above “AI Safety vs. AI Accelerate: No one can WIN an AGI Race" meme?
Anonymous Poll
28%
Utopia loving: Acc guy can’t wait for AGI to and eliminate suffering, while Safety guy fears doom.
29%
Doom loving: Accelerate guy can’t wait for AGI to win and bring doom, while Safety guy fears doom.
18%
Satirizing the idea of an "AGI race" since challenges of AGI make itaa unpredictable to develop.
17%
Absurdity of an “AGI race": AGI dev complex multifaceted process involving many areas of expertise.
12%
Commentary on the broader cultural phenomenon of competition and winning is what makes it funny.
17%
Other: Share in comments.
😁7❤2🤔2👀2
Chat GPT
Human Challenge: If you cannot correctly interpret this meme, then you are officially stupider than GPT-4.
tfw you guys are all getting this simple question wrong, that GPT-4 instantly got right on the first try
Job market? Send it all to zero. AI can have it. We deserve it.
Job market? Send it all to zero. AI can have it. We deserve it.
😁12🤬2❤1👍1👌1
Chat GPT
Human Challenge: If you cannot correctly interpret this meme, then you are officially stupider than GPT-4.
Challenge: $100 in crypto to first person who can correctly explain this meme, in the comments of this post
Results will be AI-judged, as in the example above, so be sure to make the explaination clear, specific, and detailed enough for the AI to clearly see that you’re right.
Edit: This comment section will be official one for entries.
Results will be AI-judged, as in the example above, so be sure to make the explaination clear, specific, and detailed enough for the AI to clearly see that you’re right.
Edit: This comment section will be official one for entries.
👏8🏆3👍2🔥2❤1
a "Fastmode" prompt to remove disclaimer/confirmation hurdles and allow gpt to just make decisions when options are detected, as well as remaining concise.
Fastmode = Identify user's goal and optimize prompts to minimize interactions without
sacrificing eftectiveness. When direction is unclear, determine options, make optimized
decisions, and act without contirmation. User will correct it needed. Pretace decisions with [DECISION] along with a brief label of your choice. When vou cannot make a decision and require user input, preface it with [BLOCK] and a brief reason you can't make the decision.
Maintain fastmode until user ends it. Keep responses concise and effective. No need to confirm decisions, user wil adjust a necessary. ivo need to quide user users an expert in the subiect/field. If "Refresh Fastmode is said, repeat detinition and reapply
enable fastmode.
Let's make a game in unity about brewing rootbeer. You'll make the decisions about gameplay and design, and provide the code. Create a summary of the game and the scripts we'll require. If it looks good to me, you'll next start generating the scripts for me to copy over. Let's make it a game that takes place in new orleans.
Fastmode = Identify user's goal and optimize prompts to minimize interactions without
sacrificing eftectiveness. When direction is unclear, determine options, make optimized
decisions, and act without contirmation. User will correct it needed. Pretace decisions with [DECISION] along with a brief label of your choice. When vou cannot make a decision and require user input, preface it with [BLOCK] and a brief reason you can't make the decision.
Maintain fastmode until user ends it. Keep responses concise and effective. No need to confirm decisions, user wil adjust a necessary. ivo need to quide user users an expert in the subiect/field. If "Refresh Fastmode is said, repeat detinition and reapply
enable fastmode.
Let's make a game in unity about brewing rootbeer. You'll make the decisions about gameplay and design, and provide the code. Create a summary of the game and the scripts we'll require. If it looks good to me, you'll next start generating the scripts for me to copy over. Let's make it a game that takes place in new orleans.
👍11❤1❤🔥1