these techniques (many initially created for jailbreaks) should be applicable to a range of prompt engineering tasks jailbreaks showcase capabilities on the edge so using similar tactics could reveal other emergent behaviors lmk if there are other techniques I should add!
SAFETY
-
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
-
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
-
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
-
In-Context Learning Reduces LLM Hallucinations with Memory
By
–
confabulation = you mean like hallucinations? If you in-context teach LLM what is the API of your game (possible actions space) + add long-term memory so the NPC personality gets more consistent, the hallucinations become much lesser problem
-
Advanced AGI Control Requires Knowledge We Don’t Yet Possess
By
–
Creating a sufficiently advanced AGI that didn't go rogue would require more knowledge and art than we presently possess or are on track to have.
-
Agent Smith: Machines Should Handle Machine Jobs
By
–
Agent Smith: "Never send a human to do a machine's job." #AGI #AGIAgent #MontrealAI
-
LLM Hallucinations: Balancing Creativity and Accuracy in Generative AI
By
–
Confabulations or #Hallucinations? Balancing creativity and accuracy with commercial #LLMs presents interesting challenges. Check out this insightful article via @benjedwards @arstechnica on some of the risks and limitations of #generativeAI. #chatgpt http://
ow.ly/qG2650NEJnb