主题 · 概念
推理
在生产环境中运行模型：路由、成本、硬件，以及作为按量计费的公用服务的推理。
地图上 7 个页面及其周边主题
2026
-
笔记The window before the utility
Tokens will be a metered utility and AI as ordinary as electricity. Until then, learning to use it well is an advantage that will not come around again.
-
笔记Opus 5.5 is the best Opus since 4.5
A month in, Claude Opus 5.5 feels like the next milestone after Opus 4.5: the same jump in what Claude Code can carry, now faster and cheaper per task.
- 14 分钟
The Model Is a Dependency
Every layer of the harness has existed to put the right tokens in front of one hardcoded model string. This post pulls that string out and makes the model a dependency: why you route a cheap model for easy turns and a strong one for hard turns, what a fallback looks like when a provider is down, and why 'models are commodities' is a claim about your architecture before it is a claim about the market. Part seven of The Agent Platform Handbook.
- 12 分钟
Brain Emulation, Read as an Infrastructure Problem
An MIT thesis argues brain emulation has crossed into engineering. Read as infrastructure, the numbers describe a workload your AI cluster was not built for.
- 12 分钟
The Economics of Inference
Inference tokens are not API calls. They are a metered resource that is consumed, generates value, and correlates with power draw. The economics of the post-AI world look less like software and more like water, electricity, and gas.
- 23 分钟
What Comes After the Last Programming Language
If AI generates machine code directly, why are we still running operating systems designed for humans? The answer might be an inference-native OS.
- 23 分钟
Archipelag.io Is in Open Beta: Here's Why I Built It
From watching Ethereum miners in 2016 to building a decentralized compute network in open beta. Architecture, conviction, and the long road.