Submissions from stephantul.github.io

		Hiding a Prompt in a Tokenizer (stephantul.github.io)
		2 points by stephantul 20 days ago \| past
		From Chesterton's fence to Chesterton's gap (stephantul.github.io)
		86 points by stephantul 88 days ago \| past \| 56 comments
		Why scikit learn's fit transform is probably not for you (stephantul.github.io)
		1 point by stephantul 3 months ago \| past
		Turning any tokenizer into a greedy one (stephantul.github.io)
		2 points by stephantul on Aug 10, 2025 \| past \| 1 comment
		Decasing Transformers for Fun (stephantul.github.io)
		3 points by stephantul on Aug 1, 2025 \| past \| 1 comment
		Using overloads to handle union return types in Python (stephantul.github.io)
		1 point by stephantul on March 29, 2025 \| past \| 1 comment
		Evaluating ML classifiers using relative error instead of absolute accuracy (stephantul.github.io)
		1 point by stephantul on March 13, 2025 \| past
		Defeat stringly typing without making your users unhappy (stephantul.github.io)
		2 points by stephantul on March 7, 2025 \| past