The President of OpenAI Gives His Prompting Secrets

In partnership with

Find out why 1M+ professionals read Superhuman AI daily.

In 2 years you will be working for AI

Or an AI will be working for you

Here's how you can future-proof yourself:

1. Join the Superhuman AI newsletter – read by 1M+ people at top companies

2. Master AI tools, tutorials, and news in just 3 minutes a day

3. Become 10X more productive using AI

Join 1,000,000+ pros at companies like Google, Meta, and Amazon that are using AI to get ahead.

Sign up and start learning AI

Welcome to our AI Newsletter!

In today's edition, we're diving into the world of AI prompting with insights from none other than OpenAI's President, Greg Brockman. Recently, Brockman shared a game-changing framework for crafting the perfect AI prompt, originally developed by Ben Hylak. This four-pillar approach is designed to help users get the most out of ChatGPT O1, ensuring clear, precise, and optimized responses.

The Four Pillars of Brockman's Prompt Engineering Framework

1. Defining the Goal

Brockman emphasizes the importance of clarity when setting your objective. Vague requests lead to vague answers, so being specific is key4.

Why it works: By clearly defining your goal, you help the AI filter out unnecessary information and focus on providing relevant, targeted responses.

2. Specifying the Return Format

This pillar focuses on instructing the AI on how you want the information presented4.

Why it works: By specifying the format, you ensure that the AI's response aligns with your needs, whether it's a list, a comparison table, or a detailed analysis.

3. Providing Context

While not explicitly mentioned in the search results, providing context is crucial for getting accurate and relevant responses.

Why it works: Context helps the AI understand the background of your query, leading to more tailored and insightful answers.

4. Setting the Role

Brockman's framework likely includes setting a specific role for the AI to assume when responding to your prompt12.

Why it works: Role-playing allows the AI to tap into specific knowledge domains and perspectives, resulting in more specialized and authoritative responses.

By following Brockman's framework, users can craft prompts that elicit more precise, structured, and valuable responses from ChatGPT O1. This approach not only improves the quality of AI-generated content but also enhances the overall user experience by reducing the need for multiple iterations to get the desired information.

Stay tuned for our next newsletter! Chat soon 🙂