AI article
Stop counting tokens, start counting what ships
Publisher description: When a developer gives an AI agent a coding task, the agent does more than answer once. It plans, generates code, runs tests, and repeats the process to correct errors. A single task can use 10 to 50 times more tokens than a basic chat prompt. The more useful the agent becomes, the more calls…
MIT Technology Review | Nov 2, 2026 | Affan Syed
Automated excerpt
Cost per token measures consumption, not results. Second, it tracks cost per merged pull request, because it connects AI spending to software that ships. To learn more about HPE Private Cloud AI, please visit HPE.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.