AI
llms.txt: Making AI Understand Your Website
· β˜• 14 min read
1. What llms.txt Is llms.txt is a convention: put a Markdown file at the root of your site, and use plain language to tell large language models and AI agents what the site is, which content is worth reading, and what each piece covers. It was proposed by Jeremy Howard (Answer.

deepseek-harness-remote-node
· β˜• 9 min read
1. Insufficient Context Is the Key Constraint on AI Agent Adoption The quality of an Agent’s work depends both on model capability and on the environmental context it can reach. For development and operations, the harder part is that the environment is often fragmented: logs live on production, docs in a knowledge base, code in a Git repository.

Will the Middle Platform Disappear Under AI Agents?
· β˜• 4 min read
1. Business Bypasses the Middle Platform At the moment I work on Infra at a fairly large AI middle-platform team. After a department meeting early this year, I started wondering whether the middle platform would disappear. OpenClaw was very popular at the time. Business colleagues using OpenClaw with a large model could already get a great many things done without cooperating with other teams β€” the division of labor disappeared.

OpenSpec: A Lightweight Spec Contract for AI Coding
· β˜• 14 min read
1. What OpenSpec Is OpenSpec is an open-source Spec-Driven Development framework maintained by Fission-AI. It does not try to teach AI new coding tricks. Instead it adds a lightweight “agreement layer” between you and the AI β€” before any code is written, both sides settle on what to do, in writing.

How to Add Huawei NPU Nodes to a Kubernetes Cluster
· β˜• 10 min read
1. Disk Handling 1.1 Inspect Disks Inspect the new disk 1 fdisk -l Disk /dev/nvme1n1: 3.91 TiB, 4294967296000 bytes, 8388608000 sectors 1.2 Build a RAID0 If you have several small disks, a better approach is to build a RAID0 β€” this gives you not only a larger storage directory but also higher speed.