Category
8 articles in this category.
Written by me.
Cloud bills grow from small decisions repeated at scale. Read where cost comes from, a worked example, and why a smaller instance is not always cheaper.
A factor tilt has costs beyond the expense ratio. Read what they are, a worked example, and why a backtest is not a promise.
Inference cost is set by how tokens are served, not just by the price per token. Read the pitfalls, a worked example, and why cache misses are expensive.
A review consumes time and attention, not just a form. Read the real costs, a worked example, and why a rating is not a result.
Caching is easy to enable and easy to get wrong. A checklist maps stable prefixes and cache boundaries to a real cost decision, with claim status explicit.
A token price is not a monthly bill. Read the four inputs that determine spend, a worked estimate, and the costs that surprise teams.
Many requests share the same long prefix. Read how caching bills that prefix, a worked saving example, and why cache misses happen.
More thinking at answer time can beat a bigger model. Read the research, a worked budget, and when the trade-off pays.