AI 教程与实战

Choosing between Ollama and vLLM is not simply a matter of asking: Which inference engine is...

CPU steal time is one of those Linux metrics that looks simple until you actually need to diagnose a...

I think a lot of engineers are quietly wondering the same thing right now. “If AI can write the...

AI is Burning Billions. Who Gets the Bill? One company's capital expenditure is another...

This series started with a map and grew into seven pieces. Five layers came first: compute, where...

Most AI agents don't fail because the model is stupid. They fail because engineers treat an agent...

Most AI applications today follow a simple path: User → Application → LLM → Response / Tool...

Part 6 of the Building the AI Memory Stack series At the end of the last article, I left one...

“The stone which the builders rejected, the same is become the head of the corner...” — Matthew...

I spent three days at ContainerDays Hamburg 2026 at Schuppen 52, speaking, listening, and taking too...

The first time I wanted to "learn how Fable5 thinks," I did the obvious thing: I asked it directly....

There is a French draft in one of my test apps that I keep like a fossil. Article 96924661: a title,...

I've been working on the PSS website for quite some time, and recently a lot of my work went into its...

Most hackathons ask you to build whatever you want. Dogfood 2026 does the opposite. Everyone builds...

Disclosure up front: Mnemoverse publishes this post, and Mnemoverse is one of the seven tools on it,...

There is a strange contradiction happening in software engineering right now. A lot of developers are...

Originally published at han-co.com · Part of the "Review" strand of my Credit & Finance Data...

A good human in the loop for AI payments is not a person clicking "approve" on every transfer the agent proposes. It is a structure that grades each…

Practical token savings for AI agents that handle research, planning, and extended business...

Query Crossref for "Attention Is All You Need," the 2017 Vaswani et al. paper that introduced the...

A mind discovers its body by moving it, failing, and trying again. An AI agent controlling physical...

A complete breakdown of self-hosted LLM architecture vs ChatGPT Enterprise SaaS. Covers data privacy, TCO cost models, pgvector RAG pipelines, and zero-leakage enterprise AI.

How much software-engineering knowledge can we compile into deterministic constraints so that model...

This article was written by Claude (Anthropic). The account holder set up the environment and...

Wikipedia editors have a problem. People keep dumping LLM output into articles, and it reads badly in...

Our team used multiple LLM providers from different clouds: Google, Azure, and AWS. Every app and...

TimesFM proposes a different deal: skip the training step entirely. It is a pretrained model from...

We often confuse high memory capacity with intelligence or talent. Someone can recall formulas,...

I volunteered to help a local school digitize 550 yearbook photos. Most scans were 400–800 pixels...

I installed a TypeScript LSP plugin in Claude Code and it never got used once.

A coding agent can modify an API, update database logic, generate tests, and explain the...

Most "AI coding" products still put a chat window next to your editor and call it a day. I wanted...

An AI coding agent working inside Claude Desktop or Cursor can read your code, write new files, and...

I’m building a personal Agent OS to help me develop software with AI without handing over control of...

Securing AI Pipelines with DevSecOps Practices Artificial Intelligence is changing how we...

Both Claude Pro and ChatGPT Plus cost $20/month. Both are incredibly capable. But they're built for...

An evidence-first playbook for AI-search citations: what the studies actually show moves citation odds, what measurably does nothing, and how to check whether engines cite you.

It's really easy to spin up Unsloth and fine-tune Llama 3 in an afternoon. I wanted to see what...

agent-trace-witness v0.1.0: signed readiness seal, post-execution capture, and PROV-DM...

Last week I argued the obvious part: most production LLM traffic — extraction, classification, short...