GPT-4 Custom Instructions To Optimize Python Code Creation

Author(s): John Loewen, PhD

Originally published on Towards AI.

Python Plotly dashboard code in less than 10 minutes
Dall-E 2 image: impressionist painting of prompting GPT-4

As a comp sci professor, over the past 8 months, I have heavily integrated GPT-4 into my data visual creation workflow.

I have also noticed significant improvements in the way that GPT-4 handles data visualization requests.

However, there are still some daily frustrations that I encounter within my GPT-4 prompting workflow — specifically related to 2 issues:

GPT-4 often loses its “train of thought” from the start to end of a conversation, particularly as the responses become more complex.GPT-4 “makes up” data (and data field names) if it cannot find the actual data or field names that it needs. It calls it “placeholder” data.

To mitigate these two issues, I have discovered a tool and method that I am now integrating into my prompting workflow.

I am creating customized system prompts using the GPT-4 Custom Instructions tool.

Let me show you how it works.

With GPT-4 system prompts allows us to provide instructions to the LLM that it will remember for the entirety of a chat conversation.

Why is this important? We absolutely want to avoid the situation where we are asking GPT-4 to perform a number of tasks in sequence, and in the middle of the tasks, it completely forgets… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI