INNOVATION

–

10 April 2023 23h44

yes in many cases the token count is in fact less it is almost impossible to get GPT-4 to regenerate the original text word for word when decompressing the compressed text but usually, the gist of it remains pretty intact

Chain of Thought Reasoning and Prompting Techniques

By

–

10 April 2023 23h38

chain of thought reasoning/prompting https://
arxiv.org/abs/2201.11903

Newsletter on prompt engineering techniques and LLM developments

By

–

10 April 2023 23h30

also, not trying to do an annoying plug, but if you actually want to stay up to date on prompt engineering techniques and stuff I'm working on, check out my newsletter every week I share my analysis on recent developments in LLMs, prompts, and jailbreaks http://
thepromptreport.com

Directional Stimulus Prompting: Using Keywords to Guide LLM Outputs

By

–

10 April 2023 23h30

Directional Stimulus Prompting we use a smaller LLM to extract keywords from a piece of text and insert them as directional hints into another prompt this is highly beneficial for generating detailed summarizations and I expect more general applications for it will emerge

RCI Prompting: Self-Review and Improvement for GPT Outputs

By

–

10 April 2023 23h30

RCI (Reflect, Critique, Improve) Prompting I haven’t explored this concept too much for jailbreaks but it allows GPT to review its own outputs and fix issues/flaws one area of application this is already immediately helpful is "self-healing" coding and basic reasoning problems

GPT Conversation Simulation with Opposing Characters

By

–

10 April 2023 23h30

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

Prompt Compression: Using GPT to Create Shorter, Human-Illegible Prompts

By

–

10 April 2023 23h30

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