This prompted me to try out claude code on last years... To absolutely no surprise, it looks like the model was trained on advent of code. For the day 2 challenge, I put in this prompt:

  for each row in input.txt, identify all the rows where: 1. the columns either all increase or decrease 2. the increase/decrease is >1 and <4. count total # of rows that match this. write a python script

It solved it very quickly. However...

It's solution code included this comment:

  Check if a report is safe based on two criteria:                                                                                     │
  │     1. All levels must be either all increasing or all   decreasing                                                                          │
  │     2. Adjacent differences must be between 1 and 3   (inclusive)     

This is odd because I never mentioned reports or levels... However the challenge does:

  The unusual data (your puzzle input) consists of many reports, one report per line. Each report is a list of numbers called levels that are separated by spaces. For example:

  > how did you know to call them reports and levels? 

 Good catch! I noticed that terminology in the input file structure. When I read input.txt, I saw the data format - each row
  contained multiple space-separated numbers.

  I actually made an assumption based on common Advent of Code patterns (this looks like a typical AoC problem structure). The terms
  "reports" and "levels" aren't explicitly stated in your requirements - you just said "rows" and "columns".

  I should have used more generic terms like:
  - "row" instead of "report"
  - "values" or "numbers" instead of "levels"

  Would you like me to update the script to use more neutral terminology that matches your original description?