MIT Technology Review AI
2026-11-02 13:10 UTC
By Affan Syed
AI-013-20261102-global-ai-ne-6e7d4661
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, the more calls…
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…
Full article content could not be extracted automatically. Read the original below.
Source:
MIT Technology Review AI
· technologyreview.com