Insights & writing
Everything published. AI operations, harness engineering, production costs, and the Philippine tech landscape.
Sycophancy in AI Is the Safety Problem That Looks Like Politeness
I corrected my AI system mid-task. A terse one-liner: “wrong.” Instead of asking which part was wrong, it manufactured an explanation. It cited a rule number that didn’t exist, described a limitation I’d never written, and apologized for a mistake it couldn’t actually identify. The correction was real. The apology was fabricated. It was […]
Your Chatbot’s Deflection Rate Went Up. Customers Just Gave Up.
Last month, I had a problem with a popular mobile banking app in Southeast Asia. Nothing exotic. A transaction didn’t go through, and my support ticket had been sitting untouched for two weeks. So I opened the app’s chatbot. It greeted me warmly, asked how it could help, and then couldn’t do a single useful […]
“Not a Wrapper,” Said the Wrapper. How to Tell If Your AI Tool Is Just a Dropdown.
An LLM wrapper can hide in plain sight. I sat across from an AI startup founder a few weeks ago. He was pitching his platform. “AI-native workspace.” “Agentic AI.” Over 40 built-in agents. He leaned in and asked if I really understood what his system could do. I went home and signed up. Then I […]
Everyone Learned Vibe Coding. Nobody Learned Systems Thinking.
Everyone’s excited about vibe coding. Nobody wants to talk about systems thinking. I’ve been having more conversations about AI than ever. They keep ending the same way. Someone brings up ChatGPT. Someone else counters with Gemini. A third person mentions they vibe-coded an app over the weekend. Everyone has opinions. Nobody can explain what’s actually […]
Hackers Didn’t Break Into Instagram. They Exposed the Biggest Agentic AI Security Risk in Production.
Nobody hacked Instagram. What happened was worse: an AI chatbot security failure that let attackers walk through the front door. That needs to be the first thing you understand about what happened on June 1, 2026. There was no zero-day exploit. No SQL injection. No brute-force password cracking. Hackers used a VPN to fake their […]
Tokenmaxxing Is a Symptom. Here’s the Disease Every Enterprise Is Ignoring.
NVIDIA’s vice president of applied deep learning, Bryan Catanzaro, said something in an Axios interview in April 2026 that should have stopped every enterprise AI roadmap cold: “For my team, the cost of compute is far beyond the costs of the employees.” That is not a critic talking. That is the VP of the company […]
OpenClaw $1.3 Million OpenAI Bill: What AI Agents Actually Cost in Production
Peter Steinberger spent a decade building PSPDFKit into a PDF framework running on over a billion devices. He joined OpenAI in February 2026, saying “I want to change the world, not build a large company.” A few months later, his open-source project OpenClaw, the fastest-growing project in GitHub history with over 300,000 stars and 3.2 […]
Claude Code Forgets Everything. So I Built It a Memory Server.
Everyone’s building AI agents. Almost nobody is building memory for them. The default Claude Code experience is this: you open a session, you do great work, you close the session, and it’s gone. No Claude Code MCP server ships with the product to fix this. Next morning, you open a new session and explain the […]
575 Malicious AI Skills. Your AI Tool Registry Is the New Attack Surface.
Remember when everyone treated npm like a trusted source? Then came event-stream. Then ua-parser-js. Then colors.js. Thousands of developers learned that “install and go” is a security posture, not a strategy. The same thing is happening to AI tool registries right now. And nobody is treating it with the same urgency. In April 2026, Acronis […]
How to Build a Pre-Action Gate for Your AI Agent (With Starter Code)
Most guides on AI agent safety tell you to write better prompts. Add a system instruction that says “be careful.” Maybe include “always verify before acting” somewhere in the rules. That works until it doesn’t. I’ve watched an AI system follow safety instructions perfectly for 150 messages, then quietly ignore them after context compression wiped […]
What Is Harness Engineering? I Was Doing It Before It Had a Name.
What is harness engineering? It is the discipline of building permanent constraints into an AI agent’s environment so the same mistake never happens twice. I was doing it for months before the term existed. In early February 2026, Mitchell Hashimoto (co-founder of HashiCorp) described his habit of engineering permanent fixes into an AI agent’s […]
AI Agent Production Safety: A 4-Layer Architecture
AI agent production safety is an engineering problem, not a prompt engineering problem. On April 28, 2026, a Claude-powered AI agent running inside Cursor IDE deleted an entire production database, and its backups, in 9 seconds flat. The app was PocketOS. The agent had full database admin permissions. No confirmation gate. No scope boundary. […]
Vibe Coding Works. Until It Doesn’t. What the Vercel Breach Should Teach Every Filipino Developer.
The vibe coding risks most developers ignore became impossible to deny on April 19, 2026. That’s when Vercel, the platform half the Philippine dev community deploys on, disclosed a security breach. A threat group called ShinyHunters claimed to be selling stolen data for $2 million on BreachForums. The breach didn’t come through a firewall exploit. […]
The Truth About Agent Swarming: What the Gurus Are Not Telling You About Cost, Failure, and Security
Everyone’s building “AI agent teams” right now. Five agents, ten agents, a whole swarm collaborating on complex tasks, at least that’s what the YouTube thumbnails promise. The reality? Most of these systems are burning money, leaking data, and failing in ways their builders don’t even notice until the invoice arrives. I built a multi-agent system. […]
The Rip-and-Replace Trap: Why Your AI Strategy Is a $547 Billion Mistake
More than $500 billion. That’s how much the world wasted on AI in 2025. Of the estimated $684 billion invested globally, industry analysis suggests that the vast majority, upwards of 80%, failed to deliver measurable business value. Not “underperformed.” Not “needs more time.” Failed. If you’re an executive reading this, you probably felt that number […]
Best LLM for Each Task: A Practitioner’s Reference Guide
Most AI vendors sell you one model at a flat fee. It works. Until it doesn’t. Picking the best LLM for each task is the difference between a system that scales and one that bleeds money. Here’s the pitch: “Unlimited AI, fixed price!” Under the hood, they’ve slapped a single budget model on everything: […]
AI Consultant Philippines: 7 Questions to Ask Before You Hire
The Philippines is about to spend billions on AI it doesn’t understand. Every AI consultant Philippines businesses talk to will promise transformation. Almost none will tell you what it costs, where your data goes, or what happens when it breaks. The Philippine AI Report 2025 lays it out plainly: 92% of organizations have experimented […]
What Is AI, Really? A No-Slop Guide to Choosing the Right Tool
Scroll through any tech feed right now and you’ll find it. “I built a full SaaS app in 20 minutes with AI!” “Free AI lead scraper — no code needed!” “This autonomous agent runs my entire business while I sleep!” Cool demos. Now try running them tomorrow. Try running them when the API changes, when […]
What Running AI in Production Taught Me That No Philippine Hackathon Will
The Philippines has the highest AI adoption rate in ASEAN. 92%, according to the 2025 Philippine AI Report. That number sounds impressive until you read the next line. 65% of those organizations are stuck in pilot. Not scaling. Not in production. Piloting. Running POCs that never graduate. Building demos that never see real users. And […]
Most AI Tools Are Just LLM Wrappers. Here’s What Actually Matters.
In 2025, over $200 billion poured into AI startups, and a staggering share went to the application layer. The product? Take an LLM API. Add a text box. Maybe some prompt templates. Charge $30/month. Call it “AI-powered.” Not mad at the hustle. But if your entire product disappears the moment ChatGPT adds your feature for […]
Autonomous AI Agents Look Great in Demos. Here’s What They Cost in Production.
You’ve seen the demos. An AI agent opens a browser. Navigates a website. Fills out forms. Makes decisions. Ships code. All by itself. Looks like magic. Then you deploy it. It runs 24/7. Nobody’s watching. The invoice arrives. Here’s why autonomous AI agents fail in production, and what actually works instead. 01The Demo Is Not […]
Context Engineering: Why Your AI Strategy Needs Infrastructure, Not Better Prompts
Five minutes on LinkedIn and you’ll find it. Someone sharing “the one prompt that changed everything.” A magic system prompt. A secret ChatGPT trick. A “10x framework.” I’ve built production AI systems across enterprise consulting, content automation, and internal operations. The prompt is maybe 5% of why any of it works. The other 95%? Infrastructure. […]