Andrew Mayne is an artificial intelligence developer, consultant and Wall Street Journal best selling author
Andrew is the founder of Interdimensional, an artificial intelligence service consultancy that helps companies deploy AI solutions. Prior to founding Interdimensional, Andrew was the Science Communicator for OpenAI and their first prompt engineer. At OpenAI he worked on GPT-4, ChatGPT and GPT-3, creating many of the original prompts and examples used today.
Alongside his AI contributions, Andrew writes mystery-thriller novels. His works have been nominated for the Edgar and Thriller Awards, with series featuring characters including Theo Cray, Sloan McPherson, Jessica Blackwood, and Trasker.
Andrew was also featured in the Discovery Channel Shark Week special Andrew Mayne: Ghost Diver where he used AI and stealth technology to swim next to great white sharks in the Isle of Jaws.
Consulting
Andrew Mayne offers a range of consulting services centered around artificial intelligence
AI Strategy: Design tailored AI strategies based on specific business goals and challenges, ensuring a clear path to desired outcomes.
Technology Explanation: Break down and explain the complexities of AI technology, providing clarity and understanding tailored to business contexts.
Workflow Design: Create and optimize workflows to integrate AI tools and solutions, ensuring a smooth transition and efficient operation.
Executive Briefings: Regular updates and briefings on the latest AI developments, ensuring that leadership teams remain informed and prepared.
With a hands-on approach, Andrew prioritizes clear communication, actionable insights, and practical solutions for businesses navigating the AI landscape.
Speaking
Drawing from his expertise in artificial intelligence and his tenure as the Science Communicator for OpenAI, coupled with his creative background, Andrew Mayne provides insights on technological acceleration and offers practical strategies for embracing creativity in an AI-centric landscape. He is adept at speaking to diverse audiences, from the general public to industry experts and executives.
Books
Blog
-
A simple method to keep GPT-3 focused in a conversation
OpenAI’s GPT-3 is a highly capable general language model able to talk about almost anything. While this is an advantage on one hand, it can also make keeping GPT-3 focused on one topic a challenge if you’re trying to create a special purpose chatbot. If you want GPT-3 to talk about movies with a user,… Read more
-
OpenAI API Classification Endpoint
We recently added three new endpoints to the API for GPT-3. The Classification Endpoint makes it easy to apply classification from a data set larger than what fits inside a prompt. Read more
-
How large is GPT-3’s short term memory?
TL;DR: In an API call GPT-3 can recall details from a 1,500 word article and even repeat passages verbatim. It can also repeat over 250 items from a list as it creates a completion. The concept of memory with a large language model can be a little fuzzy. There’s how much information the model possesses… Read more
-
The GPT-3 Zero Shot approach
TL;DR: For many tasks you don’t need to provide GPT-3 with examples because it already understands what you want. If you look closely at the documentation and prompts for GPT-3 provided by OpenAI you’ll notice that a number of them don’t require any examples to show the model what you want. This is because in… Read more
-
Advanced Prompt Design for GPT-3: How to make a prompt 20x more efficient
TL;DR: GPT-3 is much more capable than people realize when you utilize advanced prompt design that shows it what you want performed in a task then show it how to perform this task with a list of inputs. One of my favorite prompts in our OpenAI documentation is an example showing how to get GPT-3… Read more
-
Overclocking OpenAI’s GPT-3
Here’s a fun fact: OpenAI’s GPT-3 is actually a family of models, Ada, Babbage, Curie and Davinci that have different capabilities and speed. While Davinci gets most of the attention, the other models are amazing in their own way. Davinci is the most generally-capable model that’s exceptional at intuiting what someone wants to accomplish while… Read more
@AndrewMayne 