Martin Fowler

Xu Hao uses chain of thought and general knowledge prompting with ChatGPT when writing self-testing code

My account of an internal chat with Xu Hao, where he shows how he drives ChatGPT to produce useful self-tested code. His initial prompt primes the LLM with an implementation strategy (chain of thought prompting). His prompt also asks for an implementation plan rather than code (general knowledge prompting). Once he has the plan he uses it to refine the implementation and generate useful sections of code.

Recently I watched a fascinating call on Zoom. Xu Hao, Thoughtworks’s Head of Technology in China, explained his explorations in using ChatGPT to help build Self Testing Code. He went through the kind of interaction that works for him.

He starts with a prompt that sets the context for the application and how he wants the code to be structured.

The current system is an online whiteboard system.

To read the full article click on the 'post' link at the top.