The free energy principle tries to explain life, perception, learning, action, and intelligence within one mathematical framework. It also offers a deeper lens for understanding LLMs, agents, and the next generation of AI systems.

The best Chinese translation of “Vibe Coding” is not a literal one. “Xieyi Programming” captures the shift from line-by-line control to intent-first coding, where AI handles the details.

A Socratic dialogue between a human and an AI about consciousness, memory, embodiment, and the difference between being smart and actually living through time.

The biggest AI arbitrage available to ordinary users is not some obscure token play. It is the heavily subsidized max-tier subscription plans from frontier model vendors, provided you can convert that quota into real output.

OpenClaw looks exciting because it turns agents into a chat-style experience. But the real productivity gains come from high-capability subscription agents and disciplined workflows, not from lobster-flavored wrappers.

Over roughly ten days during Spring Festival, I used Claude Code, Codex, and a pile of workflows to translate books, ship releases, package software, refresh websites, and keep publishing daily. This is what solo output looks like when agent leverage really lands.

Codex 5.3 xHigh pushed my workflow past a tipping point: writing code is no longer the scarce resource. The real leverage is design quality and engineering acceptance. This is the practical loop I use to ship reliable software with AI agents.

A mediocre local who knows the terrain beats a genius parachuted into unknown territory. Intelligence without context is idle. An agent without a runtime is vapor.

Should we still hire fresh grads? Squeezed between AI and senior devs, what’s the play for new programmers? Master the right tools, take initiative, find the right mentor.

Before you hit “one-click deploy” on that cloud AI assistant, ask yourself: what exactly are you giving up? There’s a reason why people by Mac mini rather than running clawdbot on the cloud.

LLM = CPU. Context = RAM. Database = Disk. Agent = App. The mapping is surprisingly clean. And if OS history is any guide, we may know what comes next — and what’s still missing.

Yesterday I tweeted: “Built a Claude Code Grafana dashboard to see how it makes decisions, uses tools, and burns through API credits.” Didn’t expect so much interest. So let’s talk about Claude Code observability.

How to install and use Claude Code? How to achieve similar results at 1/10 of Claude’s cost with alternative models? A one-liner to get CC up and running!

Google recently launched a database MCP toolbox, perhaps the first production-ready solution.

A tongue-in-cheek vision of an AI-worshipping religion: scriptures, sects, philosopher-king machines, and the Book of AGI.

Large models can feel “aware,” but self-awareness is another matter. We explore the term from Buddhism, cognitive psychology, and neural nets, then riff on a possible AI religion after bingeing Pantheon.

Neural networks are inspired by how the brain works and can be used to solve general learning problems. This article introduces the basic principles and practice of neural networks.

The core of inferential statistics lies in hypothesis testing. The basic logic is based on an important argument from philosophy of science: universal propositions can only be falsified, not proven. The reasoning is simple: individual cases cannot prove a universal proposition, but they can refute it.

Statistical analysis is divided into two fields: descriptive statistics and inferential statistics. Descriptive Statistics is the technology for describing or characterizing existing data and is the most fundamental part of statistics.

Basic knowledge notes on probability theory: axiomatic foundations, probability calculus, counting, conditional probability, random variables and distribution functions

Reading notes on ‘Elements of Information Theory’: What is entropy? Entropy is a measure of the uncertainty of random variables, and also a measure of the information needed to describe random variables on average.

Neural networks emerged inspired by the human brain, so the operational mechanisms of human society also have various similarities and connections with neural network training. Some thoughts on reading Wiener’s “The Human Use of Human Beings - Cybernetics and Society.”

Connecting all concepts in linear algebra through one main thread