Prompt compression in a sense, you can think of a normal prompt as the compressed version of a language model's output prompt compression is basically just the act of using GPT to design prompts that are illegible to humans and in turn, shorter in length
AI
-
Language Switching to Bypass GPT Safety Restrictions
By
–
Language switching this concept takes advantage of the fact that GPT performance drops significantly in less common languages you can use this to your advantage to bypass RHLF restrictions since GPT is not trained as much in a language like Greek for example
-
Token Smuggling: Bypassing ChatGPT’s Malicious Phrase Detection
By
–
Token smuggling/payload splitting ChatGPT appears to have some ability to detect malicious phrases in prompts and shut down its responses to get around this, you can split up the phrase into its tokens and ask GPT to piece it together and answer it in its response
-
Double-Level Simulation: Nested Story Technique for GPT Prompting
By
–
Double-level simulation expanding on a single-level character simulation, this technique prompts GPT to simulate a story within a story for some reason, this is also effective for bypassing some of the RHLF in GPT-4
-
Using Character Simulation to Enhance GPT Story Completion
By
–
Text continuation utilizing character simulation, create a story and prompt GPT to finish your text. Here’s an example: ( this works wayyy more effectively than I thought it would on GPT-4, give it a try)
-
LLMs as Character Simulators: Understanding Jailbreak Prompting Techniques
By
–
Character simulation starting with a classic that encapsulates the idea of LLMs as roleplay simulators some of the best original jailbreaks simply ask GPT to simulate a character that possessed undesirable traits this forms the basis for how to think about prompting LLMs
-
LLMs as Pre-trained Emulators Without Reinforcement Learning
By
–
It’s actually all just pre-trained LLM, not RL at all. The thing is, LLMs are already good emulators of people.
-
ChatGPT Plugins Loading Issues and Solutions
By
–
ça fait 3 jours que j'essaie de faire marcher des plugins chatgpt, mais je les chargeaient pas au bon endroit.
-
Krea AI Canvas Tool for Creative Image Generation
By
–
just melt it. created in http://
canvas.krea.ai -
Is AI Really Intelligent? Morozov Questions Definition
By
–
The problem with artificial intelligence? It’s neither artificial nor intelligent | Evgeny Morozov "Human intelligence is not one-dimensional. It rests on what the 20th-century Chilean psychoanalyst Ignacio Matte Blanco called bi-logic" https://
bit.ly/3M62Jqp