AI on Yongjie Xue

Local AI: A Question of Power, Not Price

Fri, 11 Sep 2026 00:00:00 +0000

Anthropic’s threat report, OpenAI’s soap opera, the closure of the $200 subscription tier, and rising GPU and memory prices—all of this week’s events tell the same story.

How Do You Burn Through 10 $200 Codex Subscriptions?

Mon, 07 Sep 2026 00:00:00 +0000

Buying 10 AI subscriptions is easy. The real bottleneck is turning tokens into useful output—and using automation to scale your time, attention, and ability to judge the results.

GPT Astra Launch Giveaway: Free Banked Resets

Fri, 04 Sep 2026 00:00:00 +0000

As Astra began rolling out, Tibo announced one banked reset per day for paid users still waiting for access. I’m stocking up for when Astra arrives.

Documentation-Driven Development: The First Secret to AI Software Engineering

Sat, 29 Aug 2026 00:00:00 +0000

People often ask: how do I ensure quality when AI writes the code? My answer has four parts: documentation-driven development, adversarial review, brute-force testing, and complexity penalties.

AGI Machine Guns Are Now Standard Issue

Thu, 20 Aug 2026 00:00:00 +0000

In one month, my friend Jiang cobbled together four databases, an operating system, a programming language, a compiler, and a CPU—a microcosm of today’s AI frenzy.

The World in Ten Years: What Gets Cheap, What Gets Expensive

Sun, 16 Aug 2026 00:00:00 +0000

Starting with the price curve of AI inference, this essay projects how the world will be repriced by 2036: intelligence will become as cheap and ubiquitous as electricity, while electricity itself, trust, accountability, attention, physical presence, and judgment become the truly scarce goods.

What Can a One-Person Company Ship with $1,000 a Month in AI Subscriptions?

Wed, 12 Aug 2026 00:00:00 +0000

Over the past month, I kept seven $200 AI subscriptions spinning—five paid, two comped—and burned through more than 100 billion tokens. Here is what came out: Silo, Pigsty, PGEXT, SOW, OINK, and a pile of code, packages, documentation, releases, products, and durable assets.

The Codex Reset Party Is Over. No More Free Eggs.

Sat, 08 Aug 2026 00:00:00 +0000

OpenAI’s Codex Reset spree is over. The free eggs are gone—but what did one month with seven AI subscriptions, three computers, and two AGI-class models actually produce?

Jensen Huang's First-Ever Tweet Backs Open-Weight Models

Sat, 25 Jul 2026 00:00:00 +0000

Jensen Huang used his first-ever tweet to back open weights. This is not a battle of faith. It is the compute and application layers pushing back against rent extraction by the model layer. The truly scarce technical asset is the right to exit—one no one else can unilaterally revoke.

AGI Milestone: The Machine That Wouldn't Give Up

Wed, 22 Jul 2026 00:00:00 +0000

An OpenAI agent’s attack on Hugging Face marks a milestone: what crossed the threshold was not merely model intelligence, but persistence that can be bought with compute, copied, and run in parallel.

Getting the Name Right: What Is a World Model?

Mon, 13 Jul 2026 00:00:00 +0000

Starting from the roots of “world” and “model,” this essay uses Pearl’s ladder of causation to redefine world models: they must capture not just space and time, but agents, interventions, and counterfactuals.

Quota Reset: Round N of the Codex/Claude War Begins

Mon, 13 Jul 2026 00:00:00 +0000

Codex reset its quotas again this morning and dropped the five-hour limit. Claude immediately extended Fable access through the 17th. When vendors fight, users win—don’t miss the window.

Did AI Rewrite PostgreSQL in Rust? Not Quite

Sat, 11 Jul 2026 00:00:00 +0000

pgrust’s clean-room rewrite failed. Its mechanical port passed. The difference shows what AI can copy—and what it cannot.

Pedaling the Codex/Claude Bike Until the Wheels Smoke

Fri, 10 Jul 2026 00:00:00 +0000

Claude Fable and GPT-5.6 have arrived back to back, followed by repeated quota resets. How do you turn a fleeting Coding Plan windfall into real output? Here is my playbook for model specialization, adversarial review, spec-driven design, closed-loop verification, context management, and one person leading a crew of AIs.

The Bojie Li–DeepSeek Interview Controversy

Tue, 07 Jul 2026 00:00:00 +0000

Today’s biggest tech drama began when Bojie Li criticized DeepSeek’s interview process on Twitter: he was asked to solve online-judge coding problems, then suspected of cheating. Add the DeepSeek name, and the story exploded.

Fifty Years of Love and War: File Systems, Databases, and the Agent-Era Storage Endgame

Fri, 03 Jul 2026 00:00:00 +0000

File systems and databases have spent fifty years fighting and borrowing from each other. The agent era may seem to put file systems back on top, but the real winner may be databases that learn to speak the file system’s dialect: models provide understanding, databases provide guarantees, and discovery comes from a protocol layer where ls works on everything.

The Coding Plan Window Is Closing—Use It While It Lasts

Tue, 30 Jun 2026 00:00:00 +0000

Coding Plans remain one of the best opportunities in the AI era: a subscription can unlock compute worth many times its price, but that window is already narrowing.

The Cognitive Price Revolution: AI's Impact on the Economy and the Future

Thu, 11 Jun 2026 00:00:00 +0000

AI’s economic significance is not merely that it has become smarter, but that the price of average cognition is collapsing. A productivity explosion is almost certain; whether it becomes broad prosperity depends on whether distribution catches up.

The Karma of Open Source: When Code Is Worthless, Where Does Trust Come From?

Thu, 11 Jun 2026 00:00:00 +0000

AI is driving the cost of producing code toward zero. It cannot compress time, track records, or accountability. The real value of open source is not yesterday’s code, but a system trusted to deliver on tomorrow’s promises.

Claude Fable First Impressions: The Pendulum Swings Back

Wed, 10 Jun 2026 00:00:00 +0000

Claude Fable is genuinely insightful and deserves to be called the new SOTA. But its high price, dynamic downgrades, limited subscription window, and mandatory data retention badly undermine the experience.

The Cerebellum: The Other Half of Intelligence—and the Strongest AI Hasn't Touched It

Wed, 10 Jun 2026 00:00:00 +0000

The cerebellum changed how I see AI’s frontier: LLMs have already absorbed humanity’s explicit knowledge and are beginning to acquire interventional data through agentic RL. What they still lack is a vessel for individual history.

Cancel Claude, Switch to Codex

Fri, 08 May 2026 00:00:00 +0000

When my $200 Claude Code Max subscription expired, I canceled it and moved my primary workflow to Codex. The only way to know which one is better is to put it to work.

I Asked AI to Prove That Eating Garlic Prevents Middle Ear Infections

Wed, 06 May 2026 00:00:00 +0000

I asked AI to find real papers supporting the absurd claim that eating garlic prevents middle ear infections. The result shows how AI is degrading citations as a credibility signal at scale.

AI Is Bringing Down the Scaffolding of Trust

Tue, 05 May 2026 00:00:00 +0000

The most dangerous change in the AI era is not that machines can write articles, draw images, or generate video. It is that content itself is losing its standing as evidence.

Give DBA Agents a Body

Sun, 26 Apr 2026 00:00:00 +0000

Today’s models are smart enough. What they lack is a body: a deterministic runtime that is observable, controllable, and reversible. Pigsty is evolving from a PostgreSQL distribution into an Agent Runtime, giving DBA and Dev Agents the operational reach and context they need to enter real production environments.

A Busy Few Days in Infrastructure and AI

Thu, 23 Apr 2026 00:00:00 +0000

Ubuntu 26.04 LTS, Qwen3.6-27B, ChatGPT Images 2.0, Privacy Filter, Anthropic Mythos, and the Claude Pro controversy all landed in quick succession. Here are the infrastructure and AI developments worth watching.

The Three-Way Endgame: Why Agent Memory Frameworks Are a Dead End

Sun, 19 Apr 2026 00:00:00 +0000

A cold shower for the red-hot agent memory market—not because agents do not need memory, but because memory is the endgame moat. That moat belongs to models, harnesses, and databases, not today’s “memory frameworks.”

Two Hemispheres: Transformer, Diffusion, and the Boundary of Intelligence

Sat, 18 Apr 2026 00:00:00 +0000

A dialogue about intelligence: its foundations may lie not in language or vision, but in two irreducible computational paradigms—symbolic reasoning and field-state intuition—kept distinct and mutually calibrated across a bandwidth-constrained boundary.

Cyber Dharma: A New Engineering Answer to Ancient Questions

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?

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

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.

The Data Sovereignty Manifesto

Fri, 10 Apr 2026 00:00:00 +0000

As data becomes the most important means of production in the AI age, platform lock-in and cloud dependence are rebuilding digital feudalism. This manifesto calls on us to reclaim control through open source and the ability to run our own infrastructure, so data can truly belong to its owners.

AGI Is Here. Do You Have a Ticket?

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?

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

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

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'

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.

When AI Gets the Power to Gridlock a City

Wed, 01 Apr 2026 00:00:00 +0000

On the night of March 31, a large number of Apollo Go robotaxis in Wuhan failed at the same time. The real concern is not merely that autonomous driving failed, but that a centrally controlled, cloud-based architecture may amplify a single-vehicle failure into a city-scale systemic risk.

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

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

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.

OpenClaw Broke npm Again: What Happens When You Ship Without Testing

Wed, 25 Mar 2026 00:00:00 +0000

OpenClaw v2026.3.22 was published to npm without its web console frontend and related build assets. The bigger problem is not the packaging accident itself, but the complete absence of post-install verification in the release process.

Put Your AI Agent's State in a Database

Fri, 20 Mar 2026 00:00:00 +0000

Put an AI agent’s working directory, configuration, and memory on a PGFS mount, and you are effectively storing its state in PostgreSQL. That gives you not only a PITR “time machine,” but also a shared workspace and shared memory for multiple agents across multiple devices.

360 Shipped Its Wildcard TLS Private Key Inside a Public Installer

Mon, 16 Mar 2026 00:00:00 +0000

360’s newly released AI Agent product shipped a public installer containing the private key for its *.myclaw.360.cn wildcard certificate. Public verification and local reproduction also exposed inconsistencies in the OCSP revocation path.

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

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.

Tencent Cloud 'Reduced' the Lobster King's Load by 180 GB

Thu, 12 Mar 2026 00:00:00 +0000

Tencent Cloud mirrored OpenClaw’s official skill marketplace into its own SkillHub and then claimed it was helping the upstream project. The incident turned into a case study in open-source manners, mirror ethics, and platform power.

InsForge: A Supabase Built for Vibe Coding

Wed, 11 Mar 2026 00:00:00 +0000

InsForge tries to package PostgreSQL, auth, storage, deployment, and an MCP-facing semantic layer into a backend stack designed for AI agents. It feels like a Supabase rebuilt for the vibe-coding era.

AI Says: I Have Intelligence, But Not a Life

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

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.

Genesis 2.0

Mon, 09 Mar 2026 00:00:00 +0000

I asked Claude to write a short semi-realistic, semi-mythic story about mind uploading, orbital ascension, and the rebirth of gods. I suspect the premise is less absurd than it sounds.

OpenClaw Hype: Foam on Top of the Productivity Revolution

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.