Production on Chen Kai Blog

OpenClaw QuickStart (10): Production Deploy and the Failure Modes Nobody Warns You About

Fri, 17 Apr 2026 09:00:00 +0000

The local install gets you to ‘it works on my machine.’ The server install ensures it survives a kernel update.

This chapter walks through the deployment I use on a 2-core 4GB ECS box and the common failures I’ve documented.

Choosing your server#

LLM Engineering (12): Production — Deployment, Monitoring, Cost

Tue, 07 Apr 2026 09:00:00 +0000

This is the last chapter. The previous ones covered building the model, the prompt, the retrieval, and the evaluation. This chapter focuses on maintaining it without breaking the bank. Production LLM serving is more like running a high-traffic web service than classical ML serving, except each web request costs money and can take up to two minutes.

I’ll focus more on numbers here than in earlier chapters. In production, the difference between a profitable feature and a money pit often boils down to a 2-5x cost factor that no one is tracking. The most useful skill to develop is back-of-the-envelope cost arithmetic for LLM workloads. The numbers below are accurate as of late 2025 / early 2026; verify them against current pricing before committing.

Kernel Methods (8): Deep Kernel Learning vs Deep Learning — A Practitioner's Guide

Thu, 30 Dec 2021 09:00:00 +0000

In 2026, why are you still reading about kernel methods? Aren’t transformers supposed to have eaten the entire ML stack? Yes and no. Transformers eat the headlines, but kernels still eat the corners — the regimes with 200 samples, the regimes where the model has to publish calibrated error bars, the regimes where a physicist needs to know which basis function caused the prediction. This final part is the field manual: when kernels actually win, how to debug them when they don’t, and how to bolt them on top of a neural network when you want the best of both worlds.