ReportingVerified newsroom

Stop counting tokens, start counting what ships

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…

MIT Tech Review AI· Affan Syed·Monday, November 2, 2026 at 1:10 PM UTC
OA
OpenAI
Frontier AI lab · OpenAI
Fetching source· Pulling live content from technologyreview.com…
Company hub:OpenAI News →