The fix is not smarter prompts. It is software built to meet agents halfway.
大多数人认为提高AI提示词质量是改善AI交互的关键。但作者认为真正解决方案是重新设计软件架构,使其与AI代理更好地协作,而不是改进提示词。这一观点颠覆了当前AI优化的主流方法,将焦点从AI本身转向系统设计。
The fix is not smarter prompts. It is software built to meet agents halfway.
大多数人认为提高AI提示词质量是改善AI交互的关键。但作者认为真正解决方案是重新设计软件架构,使其与AI代理更好地协作,而不是改进提示词。这一观点颠覆了当前AI优化的主流方法,将焦点从AI本身转向系统设计。
This means 2.7x more tokens from the same GB300 NVL72-based infrastructure and power footprint, reducing the cost to manufacture each token by more than 60%.
大多数人认为硬件升级是提高AI性能的主要方式,但作者认为通过软件优化可以在相同硬件上实现2.7x的性能提升和60%以上的成本降低,这挑战了行业对硬件升级的依赖。这种观点暗示软件优化可能比硬件升级更具成本效益。
The template language's restrictions compared to JavaScript/JSX-built views are part of Svelte's performance story. It's able to optimize things ahead of time that are impossible with dynamic code because of the constraints. Here's a couple tweets from the author about that
It's fast. The Dart VM is highly optimized, and getting faster all the time (for the latest performance numbers, see perf.md). It's much faster than Ruby, and close to par with C++.
In the vast majority of cases there’s nothing wrong about wasted renders. They take so little resources that it is simply undetectable for a human eye. In fact, comparing each component’s props to its previous props shallowly (I’m not even talking about deeply) can be more resource extensive then simply re-rendering the entire subtree.