
"We have a budget. Should we train a bigger model or train longer?" is an arithmetic question, and the ability to do that arithmetic out loud separates candidates who have read about scaling from candidates who have used it.
Training compute is approximately six times parameters times tokens. Six, because each token costs roughly two FLOPs per parameter forward and four backward. That single relation lets you sanity-check any published run in about thirty seconds, and interviewers notice when you do.
The Chinchilla result is that for a fixed compute budget, parameters and tokens should scale together (roughly twenty tokens per parameter) and that the field had been training models that were too large on too little data. The number matters less than the shape of the claim.
Chinchilla optimizes training cost. You are probably paying for inference for years afterwards, and a smaller model trained past its compute-optimal point is often the better economic choice by a wide margin. Saying this unprompted is a strong signal in a design interview.
Knowing the disagreements is what distinguishes someone who has followed the literature from someone who has read a summary of it.

Five rounds, five different things being graded. Most candidates prepare for two of them and are surprised by the rest.

When the answer is wrong, teams reach for a better model. The document usually was never retrieved in the first place.

Loss flat, loss spiking, training down and validation up. Each shape has a short list of causes, and guessing is not one of the steps.