LLM System Design Interview, issue 3, Nov 5, 2025
The Scaling Law Playbook
AI Engineer interview at Anthropic, and the interviewer asks:
“We have a fixed compute budget - 32 H100s for two weeks. To get the best possible model, should we train a larger model on less data, or a smaller model on more data? How do you begin to answer this?”
Why elite AI engineers never guess model size - and how to use small-scale experiments to de-risk six-figure training runs.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.