这篇实测数据直接打脸了“智能体将消灭所有软件层”的论调，做AI工具和智能体开发的团队值得一看——它告诉你为什么好的CLI和SDK反而更值钱了。
Hugging Face CEO Clement Delangue通过实测数据反驳了“智能体会绕过所有工具直接调用API”的流行观点。团队在Hugging Face Hub上对Claude Code和Codex进行了约1000次分级测试，发现智能体使用优化过的CLI工具比手写curl或SDK调用节省高达6倍的token，且任务成功率更高（94% vs 84%）。他认为，在token昂贵的时代，抽象层（如CLI、SDK）是智能体的“缓存智能”，能压缩推理链，降低失败率和成本。因此，智能体不会重建一切，而是会倾向于使用最token高效的软件工具。Hugging Face本身已成为智能体使用AI的平台，两个月内收到约4900万次请求。
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for ag...
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratch and hit raw APIs. no more dev tools, no more CLIs, no more software layers. just agents and endpoints! We just tested this and the data says the opposite. We benchmarked Claude Code and Codex on real Hugging Face Hub tasks (~1,000 graded runs), with two setups: the agent-optimized hf CLI vs the agent hand-rolling curl or SDK calls from scratch. Hand-rolling burns up to 6x more tokens on multi-step tasks and fails more often (84% vs 94% task success). And that's just dropping one abstraction layer. It would obviously be orders of magnitude more tokens and a dramatically higher failure rate if the agent tried to bypass HF altogether and rebuild model hosting, versioning, and distribution from scratch. Every time an agent re-derives a workflow from raw API calls, you pay for that reasoning in tokens. every single run. a good CLI compresses that entire chain into a few high-level commands the agent can't get wrong. In a world where everyone is complaining tokens are too expensive, abstraction is leverage: thousands of hours of design decisions your agent doesn't have to re-reason about at inference time. Good tools are cached intelligence for agents! So no, agents won't rebuild everything from scratch. they'll gravitate to the most token-efficient tools, because that's what their owners pay for. The software that survives won't just be accessible to agents, it will be accurate and cheap for them to drive. We're seeing it happen with HF, which is becoming the platform for agents to use AI: ~49M requests in just two months, and growing fast! huggingface.co/blog/hf-cli-fo… 💬 24 🔄 5 ❤️ 41 👀 3129 📊 29 ⚡