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.
Autentifică-te pentru a adăuga comentarii
Alte posturi din acest grup
How is code generation with GenAI different from more "traditional" code generators? The newest memo in Birgitta Böckeler's explorations of GenAI talks abou
How is code generation with GenAI different from more "traditional" code generators? The newest memo in Birgitta Böckeler's explorations of GenAI talks abou
Many s
At Thoughtworks, we are strong practitioners of Test Driven Development (TDD). Naturally this leads to the question of how generative AI can
