Strategy 3: Split Complex Tasks into Simpler Subtasks. Examples:
– Use intent classification for relevant instructions.
– For long dialogues, summarize or filter past conversation.
– Summarize long documents piece by piece and build a full summary.
PROMPT ENGINEERING
-
Strategy 3: Split Complex Tasks into Simpler Subtasks
By
–
-
Strategy for Writing Clear Instructions to ChatGPT
By
–
Strategy 1: Write Clear Instructions. Examples:
– Include specific details for relevance.
– Ask ChatGPT to adopt a persona.
– Use delimiters for clear input sections.
– Specify steps for task completion.
– Provide examples and desired output length. -
OpenAI’s Free Prompt Engineering Guide: 6 Essential Strategies
By
–
OpenAI has released a free guide for prompt engineering. No payment required! Here's 6 essential strategies for writing the most effective prompts for ChatGPT
-
Nous Hermes Script with Correct Prompt Format Implementation
By
–
I wrote a simple script for this, so anyone can try this version of Nous Hermes using the correct prompt format with system instructions. I love MLX. Amazing work, @awnihannun
! -
7 ChatGPT prompts for fast brand creation
By
–
Creating a brand is hard. But with ChatGPT it just got much easier. Here’s 7 ChatGPT prompts for fast brand creation. Bookmark for later. 1. Suggest Brand Names Prompt:
Act as a brand naming expert. Generate a list of 10 unique and creative names for a [company -
ChatGPT Autonomously Solves Task Without Explicit Instructions
By
–
I didn’t do that, all I told in the terminal was “go have a chat with ChatGPT” and it figured out all the rest lol
-
AI Can Now Scroll and Screenshot Autonomously
By
–
You can literally tell the AI to scroll and snapshot
-
LLMLingua: Microsoft Tool on Hugging Face
By
–
HF:
https://huggingface.co/spaces/microsoft/LLMLingua -
Top 10 Ways to Boost LLM Outputs from Research
By
–
That's the top 10 surprising ways to boost LLM outputs. The full paper outlined 26 ways, but these 10 felt the most applicable after it started to get repetitive. Here's the link to the full paper: https://
arxiv.org/pdf/2312.16171
v1.pdf
…