Merge pull request #86 from fhdsl/quiz_ch6

adding a first draft of a ch 6 quiz

06-understanding_other_ppl_code.Rmd

@@ -266,6 +266,27 @@ ottrpal::include_slide("https://docs.google.com/presentation/d/1MCNeSO4aOm1iESWD
 
 (And if you do ever run across an expression like this in your code, you can check out our chapter on [refactoring code](https://hutchdatascience.org/AI_for_software/refactoring-code.html#refactoring-code) using AI to fix it!)
 
+## Limitations 
+
+Although chatbots can be extremely helpful for better understanding someone else's code, if there is a lack of annotation or documentation, it will be difficult to discern more about the context of the development.
+
+Cases where developers may not have provided context information include:
+
+1) Not stating their purpose for writing this code.
+2) Not describing what they planned to do next.
+3) Not describing (or being aware of) possible parts of the code that need updating or maybe have security or privacy issues.
+4) Not describing how they made certain decisions in the development process.
+
+Although we can't truly understand some of this information, it is however possible to get some assistance from chatbots with prompts such as:
+
+1) What do you think the purpose of this code is?
+2) What might be possible next steps to further develop this code?
+3) What are possible issues with this code, particularly for security or privacy?
+4) Why was the code possibly written with this structure? What other options are possible?
+
+Chatbot tools are also limited in terms of how up-to-date their training data is to know about current possible issues with code. 
+
+
 
 ## Hands-On Exercise 
 

quizzes/quiz_ch6.md

@@ -0,0 +1,48 @@
+
+{quiz, id: quiz_ethics, attempts: 10}
+
+## Template quiz
+
+Choose the best answer.
+
+{choose-answers: 4}
+? Which of the following is NOT an advantage of using AI language models to understand code written by someone else?
+
+C) Automatically fix bugs and errors in the code that don't need any review.
+C) Automatically generate comprehensive unit tests for the code that don't need any review.
+m) Analyze the code's structure, complexity, and potential defects.
+m) Understand comments and documentation written by other developers.
+o) Summarize large codebases.
+o) Better understand potential inefficiencies in the code.
+
+{choose-answers: 4}
+? What are some prompts that would NOT be helpful for you to better understand someone else's code?
+
+C) Why did the developer not write this in a different language?
+C) Why did the developer choose this data as an example?
+m) Can you tell me more about this package?
+m) Can you explain what each step does in detail?
+o) What does this code do?
+o) Can you tell me more about this data?
+
+{choose-answers: 4}
+? When asking about someone else's code, what should you do?
+
+C) Ask about how the AI chatbot came up with its answer
+C) Ask the AI chatbot what it thinks might be possible issues with the code.
+m) Assume that the chatbot knows all the possible issues with the code.
+m) Assume that the chatbot is always correct about the code. 
+o) Assume that the chatbot is correct about what language the code is written in.
+o) Assume that the chatbot knows who wrote the code and if you have permission to use it. 
+
+{choose-answers: 4}
+? Which of the following are NOT helpful questions to ask about someone else's code?
+
+C) What did the developer plan to further develop?
+C) Why did the developer not annotate this section of code?
+m) What does this regex indicate?
+m) What does this function do?
+o) What version of this package was likely used for this code?
+o) What does this variable or object mean?
+
+{/quiz}