A couple of weeks ago I watched a fascinating Zoom call hosted by Xu
Hao, Thoughtworks’s Head of Technology in China. He showed an
example of how he uses ChatGPT to help him code in a self-testing
style. 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.
Source: martinfowler