AI agents plan, generate code, run tests, and iterate on tasks, using 10 to 50 times more tokens than a basic chat prompt
Read the original at www.technologyreview.com→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...
Original headline: "Stop counting tokens, start counting what ships"
Coverage timeline
- Nov 2, 13:10 UTC MIT Technology Review AI lead source Stop counting tokens, start counting what ships