LLM System Design Interview, issue 1, Nov 5, 2025

The Tokenizer Trap

AI Engineer interview at Anthropic, and the interviewer asks:

We’re training a new model for the legal and medical domain. What’s the production risk of just using a standard, pre-trained Llama 3 tokenizer, and what’s your fix?

Don’t say: It’s not optimal, but the tokenizer will just use subwords for the OOV (out-of-vocabulary) terms like ‘aneurysm’. The model will eventually learn the combinations during fine-tuning.

Why reusing a general tokenizer can quietly 16x your compute bill - and how to avoid it.

The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.

Read it on Substack

Get the next one

Free on Substack. Unsubscribe in one click.