Instructor Notes

Some thoughts from the final discussion session in the course:

data analysis narrative vs. more “normal” program-to-do-some-stuff narrative
- data analysis -> validation as high-level activity that cannot be possibly outsourced: statistics offer lots of possiblities to “numerically successfully” calculate numbers, which are nevertheless not the correct answer to the data analysis question. (Note: Claudia has examples showing this depending on subtle details of the data analysis task; related pairs of tasks that lead to different calculations)
- “normal coding tasks” tend to have errors that lead to exceptions; though errors in program logic are possible here as well.
- “normal coding task” errors with AI-agents: program logic mistake may lead to wrong file getting deleted etc. => think over again what is a good narrative for the course
balance:
- ability to read code to detect bugs (in the extreme requiring super-human concentration)
- ability to formulate (here: ask for) good unit tests = high level ability

Introduction to Dataset, Task, and Using GenAI

FIXME