PROMPT ENGINEERING

→ View original post on X — @thatroblennon

Weekly Growth Systems Shared with 2000+ Founders and Creators

By

@thatroblennon

–

01 January 2023 20h50

Btw, I share proven growth systems with 2,035+ founders, solopreneurs, and creators weekly: • 1 Big how-to or story/lesson
• 1 Writing deconstruction
• 1 Tactic I use all the time
• 1 Genius AI writing prompt Join my crew:

AI Model Performance Comparison for Code Generation

By

–

01 January 2023 18h54

For zero-shot prompts with instructions text-davinci-003 does better in my experience. The text models are actually trained on just as much code as code-davinci-002.

Instruction Template Method for Synthesizing Code Files in ChatGPT

By

–

01 January 2023 11h00

A demo of my "instruction template" method for synthesizing complete code files in ChatGPT. Templates that mix literal code with inline placeholder instructions give better control over generations than using English prose.

Chain-of-Thought and Consensus Enhance GPT-3 Problem Solving

By

–

01 January 2023 10h11

Chain-of-thought allows GPT-3 to solve problems it otherwise cannot solve at all. Consensus allows it to more reliably solve problems it can only solve some of the time. Here, we use both to demonstrate multi-step reasoning and recitation of factual knowledge.

Using GPT-3 for a Step-by-Step MD5 Hash Calculation Task

By

–

01 January 2023 10h11

In the Python script generated by the first instruction template, we give GPT-3 the following prompt: Q: What is the final character of the MD5 hash of the last digit of the release year of the Grimes album "Visions"?
A: Let's think step by step.

AI Reasoning Technique ‘Let’s Think Step by Step’ Discussed with Research Link

By

–

01 January 2023 10h11

Next we apply "Let's think step by step," the method developed by Kojima et al. for improving accuracy on deductive reasoning problems. This encourages the model to lay out its reasoning, making it more likely to be right: https://
arxiv.org/abs/2205.11916

Instruction Template Prompting Method for GPT-3 Code Generation

By

–

01 January 2023 9h25

A simple demo of my "instruction template" method of prompting GPT-3, generating a Python 3 module using placeholders and notes within a template that contains only a single line of actual Python:

Complex GPT-3 Prompting Technique for MD5 Hash Determination

By

–

01 January 2023 2h38

A GPT-3 prompt in instruction-templated Python yielding a valid Python completion that prompts GPT-3 again, using zero-shot chain-of-thought consensus, to determine the final character of the MD5 hash of the final digit of the release year of the album "Visions" by @Grimezsz
.