Ai

Published on
June 21, 2026
A Token Effort
tokenization llm ai ml-systems nlp pretraining
The humble tokenizer decides what a model can ever learn. Why BPE, WordPiece and Unigram differ, and how to build, test and monitor one properly.
Published on
June 20, 2026
Lost in Translation
aws cloud-architecture ai content-moderation bedrock
A batch pipeline on AWS that puts a multimodal model at the centre, reading Korean and English marketing content for the offensive meaning that hides between the words.

A Token Effort