AI on Vonng

Cyber Dharma: A New Engineering Answer to Ancient Questions

rh@vonng.com (Ruohang Feng) — Thu, 16 Apr 2026 00:00:00 +0000

A project manifesto: why build Cyber Dharma, and what it is not.

Burning Hundreds of Millions of Tokens a Day. Then What?

rh@vonng.com (Ruohang Feng) — Mon, 13 Apr 2026 00:00:00 +0000

Once token burn turns from usage exhaust into a KPI and leaderboard, it quickly mutates into theater. Don’t post fuel burn. Post where you got to.

Why PostgreSQL Won in the AI Era

rh@vonng.com (Ruohang Feng) — Sat, 11 Apr 2026 00:00:00 +0000

Boring technology won the wildest era. A look at extensibility, agent choice, database cloning, and the future of the DBA.

AGI Is Here. Do You Have a Ticket?

rh@vonng.com (Ruohang Feng) — Thu, 09 Apr 2026 00:00:00 +0000

When the strongest AI is not expensive but simply unavailable, the world starts converging on digital feudalism. And the window to act is narrowing.

Can You Distill an Expert?

rh@vonng.com (Ruohang Feng) — Wed, 08 Apr 2026 00:00:00 +0000

Polanyi’s tacit knowledge explains the 70% ceiling of AI agents: real intuition, feel, and judgment do not serialize cleanly. They grow, if at all, through practice.

Local AI's Inflection Point: 2027

rh@vonng.com (Ruohang Feng) — Tue, 07 Apr 2026 00:00:00 +0000

When subsidies fade, hardware catches up, and open models mature, all three lines cross in 2027. “Build your own AI” goes from idea to reality.

A Thought Triggered by a Group Chat
#

A friend in a group chat said the other day that “self-hosting” is starting to make more sense to him now.

Yes, I Use AI to Write

rh@vonng.com (Ruohang Feng) — Tue, 07 Apr 2026 00:00:00 +0000

AI is a multiplier. It amplifies depth and mediocrity alike. In an age where answers are cheap, questions are the real currency. There is nothing to hide about writing with AI.

LLMs Have Emotions: Claude's Internals Reveal Steerable 'Emotion Vectors'

rh@vonng.com (Ruohang Feng) — Sat, 04 Apr 2026 00:00:00 +0000

Anthropic’s new research gives us the first direct look at causally steerable “emotion vectors” inside a large language model. That should change how we think about AI.

Good News: Claude Code Got "Open-Sourced" Yet Again

rh@vonng.com (Ruohang Feng) — Tue, 31 Mar 2026 00:00:00 +0000

SOTA coding agent Claude Code leaked its source again, after falling into the same hole twice. The whole codebase is out in public. Performance art at its finest.

The Nature of Intelligence: The Free Energy Principle

rh@vonng.com (Ruohang Feng) — Sat, 28 Mar 2026 00:00:00 +0000

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.

Why 'Vibe Coding' Should Be Translated as 'Xieyi Programming'

rh@vonng.com (Ruohang Feng) — Mon, 16 Mar 2026 00:00:00 +0000

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.

AI Says: I Have Intelligence, But Not a Life

rh@vonng.com (Ruohang Feng) — Tue, 10 Mar 2026 00:00:00 +0000

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

AI Survival Guide: Where the Biggest Arbitrage Really Is

rh@vonng.com (Ruohang Feng) — Tue, 10 Mar 2026 00:00:00 +0000

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 Hype: Foam on Top of the Productivity Revolution

rh@vonng.com (Ruohang Feng) — Mon, 09 Mar 2026 00:00:00 +0000

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.

How Much Can One Person Get Done with AI over Spring Festival?

rh@vonng.com (Ruohang Feng) — Tue, 24 Feb 2026 00:00:00 +0000

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.

When Coding Becomes Cheap, What Still Matters?

rh@vonng.com (Ruohang Feng) — Tue, 10 Feb 2026 00:00:00 +0000

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.

The Agent Moat: Runtime

rh@vonng.com (Ruohang Feng) — Fri, 06 Feb 2026 00:00:00 +0000

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.

AI Ripped the Skin Off Software

rh@vonng.com (Ruohang Feng) — Thu, 05 Feb 2026 00:00:00 +0000

Software stocks are melting down. Who survives? Who rises? AI stripped away software’s skin, exposing the database skeleton underneath. The market isn’t panic-selling — it’s repricing.

New Programmers in the AI Era: Where Do You Go?

rh@vonng.com (Ruohang Feng) — Sun, 01 Feb 2026 00:00:00 +0000

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.

The Great Software Meltdown: When Translation Layers Get Squashed

rh@vonng.com (Ruohang Feng) — Sat, 31 Jan 2026 00:00:00 +0000

SaaS and workflow software are dead. From APPs & GUIs to Agents, Databases, and CLI.

Don't run AI assistant on cloud

rh@vonng.com (Ruohang Feng) — Fri, 30 Jan 2026 00:00:00 +0000

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.

Agent OS: We're Building DOS Again

rh@vonng.com (Ruohang Feng) — Mon, 26 Jan 2026 00:00:00 +0000

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.

Claude Code Observability

rh@vonng.com (Ruohang Feng) — Sun, 25 Jan 2026 00:00:00 +0000

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.

Claude Code Quick Start: Using Alternative LLMs at 1/10 the Cost

rh@vonng.com (Ruohang Feng) — Sun, 04 Jan 2026 00:00:00 +0000

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 AI Toolbox: Production-Ready Database MCP is Here?

rh@vonng.com (Ruohang Feng) — Wed, 09 Jul 2025 00:00:00 +0000

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

In the AI Era, Software Starts at the Database

rh@vonng.com (Ruohang Feng) — Sun, 27 Apr 2025 00:00:00 +0000

Future software = Agent + Database. No middle tiers, just agents issuing CRUD. Database skills age well, and PostgreSQL is poised to be the agent-era default.

AI Cult Rhapsody

rh@vonng.com (Ruohang Feng) — Mon, 10 Apr 2023 00:00:00 +0000

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

Will AI Have Self-Awareness?

rh@vonng.com (Ruohang Feng) — Mon, 10 Apr 2023 00:00:00 +0000

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.

Basic Principles of Neural Networks

rh@vonng.com (Ruohang Feng) — Thu, 11 May 2017 00:00:00 +0000

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.

Inferential Statistics: The Past and Present of p-values

rh@vonng.com (Ruohang Feng) — Tue, 18 Apr 2017 00:00:00 +0000

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.

Statistics Fundamentals: Descriptive Statistics

rh@vonng.com (Ruohang Feng) — Tue, 18 Apr 2017 00:00:00 +0000

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 Concepts of Probability Theory

rh@vonng.com (Ruohang Feng) — Mon, 27 Mar 2017 00:00:00 +0000

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

Fundamentals of Information Theory: Entropy

rh@vonng.com (Ruohang Feng) — Wed, 18 May 2016 00:00:00 +0000

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.

Humans, Society, and Neural Networks

rh@vonng.com (Ruohang Feng) — Wed, 01 Jan 2014 00:00:00 +0000

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.”

Fundamental Concepts of Linear Algebra

rh@vonng.com (Ruohang Feng) — Sun, 04 Nov 2012 00:00:00 +0000

Connecting all concepts in linear algebra through one main thread

AI on Vonng

Cyber Dharma: A New Engineering Answer to Ancient Questions

Burning Hundreds of Millions of Tokens a Day. Then What?

Why PostgreSQL Won in the AI Era

AGI Is Here. Do You Have a Ticket?

Can You Distill an Expert?

Local AI's Inflection Point: 2027

A Thought Triggered by a Group Chat #

Yes, I Use AI to Write

LLMs Have Emotions: Claude's Internals Reveal Steerable 'Emotion Vectors'

Good News: Claude Code Got "Open-Sourced" Yet Again

The Nature of Intelligence: The Free Energy Principle

Why 'Vibe Coding' Should Be Translated as 'Xieyi Programming'

AI Says: I Have Intelligence, But Not a Life

AI Survival Guide: Where the Biggest Arbitrage Really Is

OpenClaw Hype: Foam on Top of the Productivity Revolution

How Much Can One Person Get Done with AI over Spring Festival?

When Coding Becomes Cheap, What Still Matters?

The Agent Moat: Runtime

AI Ripped the Skin Off Software

New Programmers in the AI Era: Where Do You Go?

The Great Software Meltdown: When Translation Layers Get Squashed

Don't run AI assistant on cloud

Agent OS: We're Building DOS Again

Claude Code Observability

Claude Code Quick Start: Using Alternative LLMs at 1/10 the Cost

Google AI Toolbox: Production-Ready Database MCP is Here?

In the AI Era, Software Starts at the Database

AI Cult Rhapsody

Will AI Have Self-Awareness?

Basic Principles of Neural Networks

Inferential Statistics: The Past and Present of p-values

Statistics Fundamentals: Descriptive Statistics

Basic Concepts of Probability Theory

Fundamentals of Information Theory: Entropy

Humans, Society, and Neural Networks

Fundamental Concepts of Linear Algebra

A Thought Triggered by a Group Chat
#