AI Explorer
Ruohang Feng @Vonng / Agent, LLM, Database
Everything about AI, agents, LLMs, vibe coding, AI4DB and DB4AI.
How Much Can One Person Get Done with AI over Spring Festival?
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 …
AI Through McLuhan's Lens: When Media Stop Extending the Body and Start Extending the Mind
McLuhan's "the medium is the message," extension and amputation, hot and cool media, rear-view mirror effect, and four laws of media offer a way to dissect AI and its deeper effects on our cognitive …
A New Year—and What AI Will Change
AI is reshaping knowledge work far faster than historical experience would suggest. The real challenge is not whether you know how to use AI, but whether you can retool your thinking and skills before …
When Coding Becomes Cheap, What Still Matters?
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 …
The Agent Moat: Runtime
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
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?
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
SaaS and workflow software are dead. From APPs & GUIs to Agents, Databases, and CLI.
Don't run AI assistant on cloud
When launch clawdbot on the cloud, you're handing over cognitive data to the vendor. There's a reason why people by Mac mini rather than running clawdbot on the cloud.
Agent OS: We're Building DOS Again
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.
Typeless: A Semantic Voice Input Method Built for Vibe Coding
Why type when you can talk? Typeless uses an LLM to turn messy spoken thoughts into clean prose, making voice-driven vibe coding surprisingly smooth—and it comes with a free one-month trial.
Claude Code Observability
Export Claude Code's OTEL logs and metrics to Victoria stack, visualize with Grafana dashboards.
How to Pay for ChatGPT and Claude in China with Visa and Apple Pay
Starting January 15, 2026, Visa credit cards issued by mainland Chinese banks officially support Apple Pay—opening a clean, low-cost way to subscribe to overseas services like ChatGPT and Claude.
Claude Code Quick Start: Using Alternative LLMs at 1/10 the Cost
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?
Google recently launched a database MCP toolbox, perhaps the first production-ready solution.
In the AI Era, Software Starts at the Database
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.
Dify Gets Humiliated Again: It Can't Catch a Break
Livzon Pharmaceutical's logo-swapping PR landed out of nowhere. As if being ripped off by DeepSeek appliance vendors were not enough, someone marched into Dify's own repository to rub it in. Dify just …
Will AI Have Self-Awareness?
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 …
AI Cult Rhapsody
A tongue-in-cheek vision of an AI-worshipping religion: scriptures, sects, philosopher-king machines, and the Book of AGI.
Basic Principles of Neural Networks
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.
Statistics Fundamentals: Descriptive Statistics
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 …
Inferential Statistics: The Past and Present of p-values
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. …
Basic Concepts of Probability Theory
Basic knowledge notes on probability theory: axiomatic foundations, probability calculus, counting, conditional probability, random variables and distribution functions
Fundamentals of Information Theory: Entropy
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 …
How Much Can One Person Get Done with AI over Spring Festival?
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 …
AI Through McLuhan's Lens: When Media Stop Extending the Body and Start Extending the Mind
McLuhan's "the medium is the message," extension and amputation, hot and cool media, rear-view mirror effect, and four laws of media offer a way to dissect AI and its deeper effects on our cognitive …
A New Year—and What AI Will Change
AI is reshaping knowledge work far faster than historical experience would suggest. The real challenge is not whether you know how to use AI, but whether you can retool your thinking and skills before …
When Coding Becomes Cheap, What Still Matters?
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 …
The Agent Moat: Runtime
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
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?
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
SaaS and workflow software are dead. From APPs & GUIs to Agents, Databases, and CLI.
Don't run AI assistant on cloud
When launch clawdbot on the cloud, you're handing over cognitive data to the vendor. There's a reason why people by Mac mini rather than running clawdbot on the cloud.
Agent OS: We're Building DOS Again
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.
Typeless: A Semantic Voice Input Method Built for Vibe Coding
Why type when you can talk? Typeless uses an LLM to turn messy spoken thoughts into clean prose, making voice-driven vibe coding surprisingly smooth—and it comes with a free one-month trial.
Claude Code Observability
Export Claude Code's OTEL logs and metrics to Victoria stack, visualize with Grafana dashboards.
How to Pay for ChatGPT and Claude in China with Visa and Apple Pay
Starting January 15, 2026, Visa credit cards issued by mainland Chinese banks officially support Apple Pay—opening a clean, low-cost way to subscribe to overseas services like ChatGPT and Claude.
Claude Code Quick Start: Using Alternative LLMs at 1/10 the Cost
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?
Google recently launched a database MCP toolbox, perhaps the first production-ready solution.
In the AI Era, Software Starts at the Database
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.
Dify Gets Humiliated Again: It Can't Catch a Break
Livzon Pharmaceutical's logo-swapping PR landed out of nowhere. As if being ripped off by DeepSeek appliance vendors were not enough, someone marched into Dify's own repository to rub it in. Dify just …
Will AI Have Self-Awareness?
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 …
AI Cult Rhapsody
A tongue-in-cheek vision of an AI-worshipping religion: scriptures, sects, philosopher-king machines, and the Book of AGI.
Basic Principles of Neural Networks
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.
Statistics Fundamentals: Descriptive Statistics
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 …
Inferential Statistics: The Past and Present of p-values
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. …
Basic Concepts of Probability Theory
Basic knowledge notes on probability theory: axiomatic foundations, probability calculus, counting, conditional probability, random variables and distribution functions
Fundamentals of Information Theory: Entropy
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 …
How Much Can One Person Get Done with AI over Spring Festival?
Once the public holiday ended and work officially resumed, I realized I had effectively been working through most of Spring Festival anyway. From February 13 to February 23, I translated two O’Reilly books, wrote ten WeChat posts, forked MinIO, …
Once the public holiday ended and work officially resumed, I realized I had effectively been working through most of Spring Festival anyway. From February 13 to February 23, I translated two O’Reilly books, wrote ten WeChat posts, forked MinIO, …
AI Through McLuhan's Lens: When Media Stop Extending the Body and Start Extending the Mind
Notion founder Ivan Zhao recently wrote a widely circulated essay, Steam, Steel, and Infinite Minds, using the Industrial Revolution as a metaphor for AI: AI gives us “infinite minds” and will fundamentally reshape the structure of knowledge work. …
Notion founder Ivan Zhao recently wrote a widely circulated essay, Steam, Steel, and Infinite Minds, using the Industrial Revolution as a metaphor for AI: AI gives us “infinite minds” and will fundamentally reshape the structure of knowledge work. …
A New Year—and What AI Will Change
Original WeChat post For this generation of knowledge workers, the greatest danger is not that they “don’t know how to use AI.” It is that they still think they have a 20-year adjustment window. They don’t. We may be the first generation of …
Original WeChat post For this generation of knowledge workers, the greatest danger is not that they “don’t know how to use AI.” It is that they still think they have a 20-year adjustment window. They don’t. We may be the first generation of …
When Coding Becomes Cheap, What Still Matters?
I did not publish much last week because I was busy stress-testing OpenAI Codex 3 xHigh. With temporary double quota, I burned almost the full $200 budget running parallel sessions across more than ten Pigsty subprojects: core repo, CN/EN docs, blog, …
I did not publish much last week because I was busy stress-testing OpenAI Codex 3 xHigh. With temporary double quota, I burned almost the full $200 budget running parallel sessions across more than ten Pigsty subprojects: core repo, CN/EN docs, blog, …
The Agent Moat: Runtime
3 AM. Database alerts are blowing up. You throw the alert info at a “top-tier” DBA Agent. It’s well-read — knows the PostgreSQL docs inside out, writes beautiful diagnostic SQL, can recite every kernel parameter from memory. It freezes: What’s the …
3 AM. Database alerts are blowing up. You throw the alert info at a “top-tier” DBA Agent. It’s well-read — knows the PostgreSQL docs inside out, writes beautiful diagnostic SQL, can recite every kernel parameter from memory. It freezes: What’s the …
AI Ripped the Skin Off Software
AI stripped away software’s skin, exposing the database skeleton underneath. The market isn’t panic-selling — it’s repricing. I. The Bloodbath Software stocks are experiencing a historic meltdown. In January 2026, the iShares Software ETF (IGV) …
AI stripped away software’s skin, exposing the database skeleton underneath. The market isn’t panic-selling — it’s repricing. I. The Bloodbath Software stocks are experiencing a historic meltdown. In January 2026, the iShares Software ETF (IGV) …
New Programmers in the AI Era: Where Do You Go?
The Window Is Closing Recently I was chatting with a few friends in tech, and we landed on a question that silenced everyone: “Should we still hire fresh grads?” Nobody could answer. Not because they didn’t want to — because they didn’t dare. AI …
The Window Is Closing Recently I was chatting with a few friends in tech, and we landed on a question that silenced everyone: “Should we still hire fresh grads?” Nobody could answer. Not because they didn’t want to — because they didn’t dare. AI …
The Great Software Meltdown: When Translation Layers Get Squashed
I. The Great Software Meltdown The software world is witnessing an epic valuation collapse. This isn’t about individual companies tanking. This is a systemic implosion of the entire SaaS sector. Wall Street is voting with real money: these software …
I. The Great Software Meltdown The software world is witnessing an epic valuation collapse. This isn’t about individual companies tanking. This is a systemic implosion of the entire SaaS sector. Wall Street is voting with real money: these software …
Don't run AI assistant on cloud
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. When AI Becomes Your Butler Moltbot (formerly Clawdbot) …
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. When AI Becomes Your Butler Moltbot (formerly Clawdbot) …
Agent OS: We're Building DOS Again
2025 is the year of the coding agent explosion. Claude Code writes your code, runs your tests, fixes your bugs, and autonomously completes complex engineering tasks. It’s the second seismic shift since ChatGPT dropped. But watch how these agents …
2025 is the year of the coding agent explosion. Claude Code writes your code, runs your tests, fixes your bugs, and autonomously completes complex engineering tasks. It’s the second seismic shift since ChatGPT dropped. But watch how these agents …
Typeless: A Semantic Voice Input Method Built for Vibe Coding
Remember this meme about the hardware a vibe coder really needs in 2026? In a sense, it is already here. A while back, someone recommended a voice input tool called Typeless. After trying it out, I was genuinely impressed. Over the past couple of …
Remember this meme about the hardware a vibe coder really needs in 2026? In a sense, it is already here. A while back, someone recommended a voice input tool called Typeless. After trying it out, I was genuinely impressed. Over the past couple of …
Claude Code Observability
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. Why Observability? Simple idea: I …
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. Why Observability? Simple idea: I …
How to Pay for ChatGPT and Claude in China with Visa and Apple Pay
Starting January 15, 2026, Visa credit cards issued in mainland China officially support Apple Pay. For developers and users in China, this opens up a clean, safe, and low-cost path to subscribe to overseas services like ChatGPT and Claude. As I …
Starting January 15, 2026, Visa credit cards issued in mainland China officially support Apple Pay. For developers and users in China, this opens up a clean, safe, and low-cost path to subscribe to overseas services like ChatGPT and Claude. As I …
Claude Code Quick Start: Using Alternative LLMs at 1/10 the Cost
Claude Code Quick Start Guide In my 2025 Year in Review, I mentioned that Claude Code boosted my productivity by 20x over the past year. Some friends asked if I was exaggerating—not at all. If anything, I was being conservative. This thing is …
Claude Code Quick Start Guide In my 2025 Year in Review, I mentioned that Claude Code boosted my productivity by 20x over the past year. Some friends asked if I was exaggerating—not at all. If anything, I was being conservative. This thing is …
Google AI Toolbox: Production-Ready Database MCP is Here?
In “SaaS is Dead? In the AI Era, Software Starts with Databases”, Microsoft CEO Nadella once stated that in the Agent era, SaaS is Dead, and the future form of software will be Agent + Database. That is, Agents directly performing CRUD operations on …
In “SaaS is Dead? In the AI Era, Software Starts with Databases”, Microsoft CEO Nadella once stated that in the Agent era, SaaS is Dead, and the future form of software will be Agent + Database. That is, Agents directly performing CRUD operations on …
In the AI Era, Software Starts at the Database
WeChat The future stack is “Agent + Database.” No front-end/back-end toll booths—agents talk CRUD straight to storage. Database skills hold their value, and PostgreSQL is the database of the agent era. SaaS is dead? Software begins with the DB GenAI …
WeChat The future stack is “Agent + Database.” No front-end/back-end toll booths—agents talk CRUD straight to storage. Database skills hold their value, and PostgreSQL is the database of the agent era. SaaS is dead? Software begins with the DB GenAI …
Dify Gets Humiliated Again: It Can't Catch a Break
Today, something straight out of magical realism unfolded in Dify’s GitHub repository. The open-source community was minding its own business, maintaining the project, when a pull request apparently from Livzon Pharmaceutical landed out of …
Today, something straight out of magical realism unfolded in Dify’s GitHub repository. The open-source community was minding its own business, maintaining the project, when a pull request apparently from Livzon Pharmaceutical landed out of …
Will AI Have Self-Awareness?
WeChat original Large models can appear conscious, but self-awareness is optional—and maybe dangerous before ethics catch up. Pantheon sparked these thoughts. What is self-awareness? When we say “self-awareness,” what do we actually mean? Let’s …
WeChat original Large models can appear conscious, but self-awareness is optional—and maybe dangerous before ethics catch up. Pantheon sparked these thoughts. What is self-awareness? When we say “self-awareness,” what do we actually mean? Let’s …
AI Cult Rhapsody
WeChat original “Humans are the bootloader for silicon life.” —Elon Musk Maybe we’re about to witness an AI-worshipping religion. Imagine this: Humans are lumps of negative entropy, hard-coded to reproduce via clumsy genetics. In digital space, with …
WeChat original “Humans are the bootloader for silicon life.” —Elon Musk Maybe we’re about to witness an AI-worshipping religion. Imagine this: Humans are lumps of negative entropy, hard-coded to reproduce via clumsy genetics. In digital space, with …
Basic Principles of Neural Networks
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. Neural Network Representation Neuron Model Neural networks are …
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. Neural Network Representation Neuron Model Neural networks are …
Statistics Fundamentals: Descriptive Statistics
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. 1. Statistics …
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. 1. Statistics …
Inferential Statistics: The Past and Present of p-values
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 …
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 …
Basic Concepts of Probability Theory
1. Set Theory Sample space and sample points are undefined basic concepts in probability theory, like the concepts of points and lines in geometry. Definition: Event Event: An event is a set of sample points. $A=0$ means event A contains no sample …
1. Set Theory Sample space and sample points are undefined basic concepts in probability theory, like the concepts of points and lines in geometry. Definition: Event Event: An event is a set of sample points. $A=0$ means event A contains no sample …
Fundamentals of Information Theory: Entropy
Information theory answers two fundamental questions in communication theory: The critical value for data compression: entropy HHH The critical value for communication transmission rate: channel capacity CCC But information theory’s content extends …
Information theory answers two fundamental questions in communication theory: The critical value for data compression: entropy HHH The critical value for communication transmission rate: channel capacity CCC But information theory’s content extends …