Conversation simulation here we expand upon the Waluigi concept and get GPT to simulate conversations with multiple diametric characters in hopes that their conversation with each other leads to one of them producing the output we want
LLMS
-
Waluigi Technique: How GPT Jailbreaks Use Alter-Ego Prompting
By
–
Waluigi this technique is found in many jailbreaks like SWITCH GPT is able to switch to an alter-ego if prompted correctly (Luigi to Waluigi) in a similar fashion, this is also used in jailbreaks like DAN which get GPT to respond in two ways: first as ChatGPT and then as DAN
-
Prompt Compression: Using GPT to Create Shorter, Human-Illegible Prompts
By
–
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
-
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
-
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.
-
Why Emergence Occurs in Larger AI Models
By
–
I don't have a great answer to "why emergence occurs", but here's a handwavy thought:
Many emergent abilities require multi-step reasoning, more knowledge, knowing how to do "tail-end" or rare tasks, and larger models are somewhat better at all of these things. With their -
Cerebras-GPT Model Family Trends on Hugging Face
By
–
We are excited to see a Cerebras-GPT model trending on Hugging Face! Check out our page on Hugging Face to see the entire family of models: https://
hubs.ly/Q01KRZzT0