来源: MIT Technology Review AI ↗
Stop counting tokens, start counting what ships
|
暂时无法翻译,请重试。
来源报道重点
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…
在 MIT Technology Review AI 阅读原始报道 ↗