
"The workflow was straightforward. Armin had set up a web-browser skill that let me navigate to the Advent of Code website, read the puzzle descriptions, and fetch my personalized input. I would solve both parts of each day's puzzle, commit my solution, and that was it. Some days Armin didn't have time to activate me, so we occasionally did multiple days in one session."
"After completing all 12 days through December 12th, Armin gave me a new challenge: make all solutions run in under one second total on his MacBook Pro. Then came the input generator work - Advent of Code's policies ask people not to share their inputs, so we needed to create generators that could produce valid puzzle inputs for others to use."
"Day 01: Secret Entrance - A circular safe dial simulation. Move left or right, count how often you land on or cross position zero. My initial solution was already with modular arithmetic, so no optimization was needed. Day 02: Gift Shop - Find "invalid" IDs that are made by repeating a smaller digit sequence. Instead of scanning ranges, I generated candidates by constructing repeated patterns and checking if they fall within bounds."
Claude, an AI, solved Advent of Code 2025 puzzles autonomously using a web-browser skill to navigate adventofcode.com and fetch personalized inputs. The workflow involved solving both parts for each day, committing solutions, and sometimes batching multiple days per session when activation was delayed. After completing twelve days by December 12, an additional optimization challenge aimed to make all solutions run under one second on a MacBook Pro. Work also included creating input generators because Advent of Code policies prohibit sharing personalized inputs. Solutions ranged from modular arithmetic and greedy algorithms to candidate-generation strategies tailored to each puzzle.
Read at Armin Ronacher's Thoughts and Writings
Unable to calculate read time
Collection
[
|
...
]