來源: MIT Technology Review AI ↗
Stop counting tokens, start counting what ships
|
暫時無法翻譯,請重試。
來源報導重點
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 閱讀原始報導 ↗