Ask HN：公司在“代币最大化”与代币优化之间脱节了吗？
1 分•作者: mc-0•大约 1 个月前
大约六个月前，我加入了某顶级 F500 强企的一个新团队。我的新老板严格要求使用 AI，核心原则是：“你们不应该手动编写任何代码”。
从那时起，一切都围绕着代理、技能、MCP、Harnesses、定制的内部框架，以及不停地运行 Opus 4.7 high。
现在，在公司层面，正在安排“鼓励参加”的研讨会，以学习如何优化代币使用，因为 API 定价已成为企业级的常态。
我从直属领导那里得到的指示非常明确。AI / 代理主导一切，团队的期望是保持目前的速度。但事实是，大多数工程师坦诚地承认：我们对任何事情都无法完全理解。尤其因为代理也在生成架构文档、用户故事需求和验收标准的内容。
我觉得我直接负责这些工具的非确定性输出。我的主管对任何问题的解决方案都简化为“你需要使用代理、技能等”。
有没有其他人也经历过这种拉锯战？情况如何？
查看原文
About 6 months ago I joined a new team within a top ten F500 company. My new boss strictly mandated AI use with the key principle being: "You shouldn't be manually writing any code".<p>Since then its been all agents, skills, MCP, harnesses, custom in-house frameworks, and running Opus 4.7 high non-stop.<p>Now at a company level, there are "encouraged attendance" workshops getting scheduled to learn how to optimize one's token use now that API pricing is becoming the norm at an enterprise level.<p>The direction I got from my direct leadership was very direct. AI / agents lead everything and the expectation is the team moves as quickly as it has. But the truth is most engineers candidly acknowledge: we don't fully understand anything. Especially because agents are also churning out the content of architectural documentation and user story requirements and acceptance criteria.<p>I feel like this is a situation where I am directly responsible for the non-deterministic output of these tools. The solution I get from my supervisor for any problem literally boils down to "You need to use an agent, skill, etc.".<p>Is anyone else going through this tug of war? How is it going?