不必事事用前沿模型：开源模型在自动化中更划算
You do not need frontier models for everything.
You do not need frontier models for everything.
并非所有事情都需要前沿模型。
For example, open models are great for automations.
例如，开源模型非常适合自动化任务。
If you are not sure where to adopt open models, start there.
如果你不确定从哪里开始采用开源模型，就从这里入手。
It's one of the biggest changes I've made that contributed to a large percentage of my token usage moving to local or open models.
这是我做出的最大改变之一，它促使我大部分令牌使用量转向本地或开源模型。
A huge percentage of my automations consist of repetitive tasks steered via self-tuned skills.
我的自动化任务中，很大一部分是由自我调优的技能引导的重复性工作。
These skills become useful automations that work really well with these open models. I don't even need to tune the models, but that's also an option I am currently exploring for more complex tasks. The skill essentially takes care of that. And it works because of the in-context learning capabilities of these models.
这些技能变成了有用的自动化流程，与这些开源模型配合得非常好。我甚至不需要调整模型，但这也是我目前正在探索的选项，用于处理更复杂的任务。技能本身就能处理这些。这之所以有效，是因为这些模型具备上下文学习能力。
If you don't run automations, it might be hard to figure this out. But I highly recommend you start somewhere.
如果你不运行自动化任务，可能很难理解这一点。但我强烈建议你从某个地方开始尝试。
Besides ending up with more efficient automations, I've managed to significantly reduce costs. I then use that extra budget to leverage more closed frontier intelligence for other creative and research-heavy tasks.
除了最终获得更高效的自动化流程外，我还成功大幅降低了成本。然后，我将节省下来的预算用于利用更多封闭前沿智能来处理其他创意性和研究密集型任务。
That's right! I use both closed and open frontier intelligence. This is not about vendor loyalty; this is about leveraging the best of all worlds.
没错！我同时使用封闭和开放的前沿智能。这并非出于供应商忠诚，而是为了充分利用各种优势。
Something I heavily advocate for is owning the harness and the model, and this practice I feel will allow me to better tap into all flavors of intelligence (open & closed).
我极力倡导拥有控制框架和模型本身，我认为这种做法能让我更好地利用各种类型的智能（开放与封闭）。
Maybe too early, but I suspect this is going to become best practice when AI ROI dominates the discussion.
也许现在说还为时过早，但我预感当AI投资回报率成为讨论焦点时，这将成为最佳实践。
Model routing doesn't solve this. This requires tedious engineering, evals, and decision-making on your part. If you are developing your own harness, you are in the driver's seat and have more control over this important decision. This is why I strongly believe that companies will start to hire rapidly for harness engineering.
模型路由并不能解决这个问题。这需要你进行繁琐的工程、评估和决策。如果你在开发自己的控制框架，你就掌握了主动权，能更好地控制这一重要决策。这就是我坚信企业将迅速招聘控制框架工程师的原因。
I am sharing a little snapshot of one example of an automation I run daily to track AI trending stories on HN. And I have a bunch of similar ones for different sources like arXiv, X, and so on. I also use it for some proactive agent sessions that keep track of important events around projects I build. You don't need frontier intelligence for this.
我分享一个我每天运行的自动化示例，用于追踪HN上的AI热门故事。我还有一系列类似的自动化，用于arXiv、X等不同来源。我还用它来进行一些主动的代理会话，跟踪我所构建项目的重要事件。这些都不需要前沿智能。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力