Uber 工程師使用 Claude Code 時,即使模型支援 100 萬個 token,工作階段也會在 400K 個 token 時被壓縮。
- 從 2 月到 8 月,每週 AI 助理請求量增加到原來的 9.4 倍,每週活躍使用者增加到 7 倍,但整體 AI 支出自 4 月以來大致持平。
- Uber 也讓 AI 助理透過命令列工具連到中央 MCP 閘道,避免一開始就載入 100 多種工具的說明,因為這些說明會先佔用 50K 到 70K 個 token。
- 文中提到每千次請求的成本比高峰時低近 34%,每個工作階段的成本比 6 月高峰時低 52%,但沒有說明任何單一預設設定省下多少。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Uber 的案例呈現 AI 程式工具用量大增、總支出仍大致持平的情況,也說明工具描述佔用上下文時,團隊如何改用集中式 MCP 閘道。
Uber compacts engineers’ Claude Code sessions at 400K tokens, even on million-token models, after exhausting its AI budget.
Weekly agent requests at Uber grew 9.4x from February to August and weekly active users of its AI coding tools grew 7x, yet overall AI spending has stayed roughly flat since April.
With the model held constant, cost per 1,000 requests fell almost 34% from its peak and cost per session fell 52% from its June peak, but Uber gives no savings figure for any single default.
Uber still runs MCP servers, but agents reach them through command-line tools tied to a central MCP gateway, because preloading descriptions for 100-plus tools costs 50K to 70K tokens before the first prompt.