Summary
This chapter had one important purpose – to compare and contrast the experience of using ChatGPT with GitHub Copilot and, in this case, its chat function. We used an approach that consisted of providing a lot of upfront information to Copilot, by describing the overall problem and the shape of the dataset. We also provided instructions to let Copilot guide us on what to do, which showed us the steps to take gradually and what code to run. The general conclusion is that we can use roughly the same method using Copilot Chat as we did with ChatGPT.
We also saw how Copilot can help explain our output, understand where in the process we are, and suggest the next step to take.
As a rule, we should always test code and ask our AI assistant to help if it doesn’t run or produce the expected output.
Join our community on Discord
Join our community’s Discord space for discussions with the author and other readers:
...
