广场

Restructuring changkun.de

Since the “architecture upgrade” at the end of 2020, I have rarely touched the overall structure of changkun.de . At the end of The All in Go Stack , I expressed the hope that the new “organisational architecture”, backed by Go’s compatibility, would serve reliably for more than three years. Looking back now, it served for almost six years, and for most of that time it indeed had no major problems. But over those six years, more and more things accumulated on the server: whenever I needed a new feature, I would add a service, a route or a GitHub Action, and never come back to tidy up afterwards. Little by little, the website drifted back into an “organisationally chaotic” state. This weekend…

Smooth Exponentials for Robotics

I recently reread Dario Amodei’s essays "Machines of Loving Grace" and "Adolescence of Technology." In these essays and his interviews, Dario speaks often of a "smooth exponential" of AI capabilities, as if machine intelligence "emerge[s] spontaneously from the right combination of data and raw computation."

Eric JangAI 研究英文

Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops

arXiv:2611.23445v2 Announce Type: replace Abstract: Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strategies aim to rescue accuracy by selectively retaining high-precision parameters, the fundamental mechanics of where and why these models collapse remain poorly understood. In this study, we systematically analyze the anatomy of quantization collapse across standard Vision CNNs (including ResNet and EfficientNet backbones) evaluated on the full 50,000-image ImageNet-1k validation set. First, we map the exact progres…

arXiv AIAI 研究英文

Use Kimi Code CLI with models on Amazon Bedrock

Kimi Code CLI v2.7.0 adds a native Amazon Bedrock provider, so you can connect the open source coding agent to models like Kimi K3.1 Pro using your standard AWS credential chain (named profiles or SSO) instead of a separate API key. This post shows how to configure the provider and send your first request.

AWS Machine LearningAI 研究英文