Explore archetype classification pipeline in a Magic deck-tracking repo
Takeaway: Next time I'd front-load the specific files I already suspect matter (classifier.py, pipeline.py, entrypoint.py) to cut down on the exploratory grepping.
1 session on csv with a coding agent: the agent failed at least once in 0, and 1 finished without a human stepping in.
Takeaway: Next time I'd front-load the specific files I already suspect matter (classifier.py, pipeline.py, entrypoint.py) to cut down on the exploratory grepping.