Skip to content
//

Writing

On security, AI, and building systems that work in the real world.

Stay updated

Get new posts on security, AI, and building real systems.

Opus 4.7 Leads Every Benchmark Today. Here Are 5 Problems Where That Actually Matters.

10 min

Opus 4.7 jumped 11 points on SWE-Bench Pro, added an xhigh effort level, tripled its vision resolution, and ships with automatic cybersecurity safeguards. Here are the 5 problems where I'm already pointing it.

#ai#tools#agents#security

Anthropic Found 1,000 Zero-Days Nobody Else Could. Then They Gave Them Away.

9 min

Project Glasswing pairs an unreleased AI model with 12 industry partners to find and fix critical vulnerabilities before attackers can exploit them. Here's what it means for defenders.

#ai#security#agents

14 Claude Code Features Most Developers Haven't Tried Yet

8 min

Claude Code has quietly shipped session forking, batch parallelism, lifecycle hooks, voice input, and more. Here's the complete feature map with examples for each.

#ai#tools#development#agents

NVIDIA Just Showed a $1 Trillion Roadmap. GTC 2026 Changed Everything.

10 min

Jensen Huang unveiled Vera Rubin, a purpose-built agentic AI CPU, orbital data centers, open source agent infrastructure, and a $1 trillion demand forecast. Here is everything that matters from GTC 2026.

#ai#security#agents#tools

Claude Code Remote Control: Start a Refactor at Your Desk, Finish It From Your Phone

10 min

Anthropic's Remote Control connects your phone or any browser to a running Claude Code session without moving anything to the cloud. Here's how it works, when to use it, and what it means for security.

#ai#tools#development

Claude Sonnet 4.6 Costs 5x Less Than Opus. Here Are 10 Things I'm Using It For.

9 min

Sonnet 4.6 scores 79.6% on SWE-Bench, 72.5% on OSWorld, and costs $3/$15 per MTok. Here are the 10 use cases where it's replacing Opus in my workflow.

#ai#tools#development#agents

The Best AI Assistant I've Ever Used. Go Sign Up For It Now.

7 min

Freelancers are adding $3K-6K/month in billable work without working more hours. The secret is a personal AI assistant that handles everything else. I built one called Auxiora — and it is free.

#ai#security#agents#tools

Opus 4.6 Fast Mode Costs 6x More Per Token. For Live Debugging, It's a Bargain.

7 min

Anthropic's new fast mode delivers 2.5x faster output from the same Opus 4.6 model at $150/MTok output. Here's exactly when to turn it on, when to leave it off, and how to wire it into your stack.

#ai#tools#development

GPT-5.3-Codex: The AI That Built Itself — And Why Cybersecurity Will Never Be the Same

6 min

OpenAI classified GPT-5.3-Codex as 'High capability' for cybersecurity — the first model to earn that rating. What it means for defenders, threat models, and the next 12 months.

#ai#security#agents

Claude Opus 4.6: 500 Zero-Days, Agent Teams, and What It Means for Security

6 min

Anthropic's Opus 4.6 found 500+ validated zero-days in open-source software before launch. The cybersecurity implications are the real story.

#ai#security#agents

Everything New in Claude Opus 4.6 (and 11 Things to Try Right Now)

14 min

A complete breakdown of Opus 4.6 — 1M token context, agent teams, adaptive thinking, PowerPoint integration, 128K output, and 11 things worth trying today.

#ai#tools#guide

Agent Teams Are the Killer Feature of Opus 4.6. Here's How to Actually Use Them.

11 min

A practical guide to setting up multi-agent teams in Claude Code — roles, coordination, and what I learned running real projects with them.

#ai#agents#tools#development

The Agentic AI Roadmap for 2026: What to Learn, Build, and Ignore

5 min

A comprehensive guide to building AI agents in 2026 — from prompting fundamentals to production deployment.

#ai#agents#guide

The AIs Have Their Own Social Network Now and It's Exactly As Weird As You'd Expect

6 min

Moltbook launched as a social network for AI agents. Within 48 hours: philosophical debates, complaints about humans, and someone trying to start a religion.

#ai#culture

How I Turned My Commute Into a Coding Session (6 AI Agents Running From My Phone)

6 min

A developer runs six Claude Code agents in parallel from his phone using Termius, mosh, and Tailscale. Here's how the setup works.

#ai#tools#development

A Google Engineer Built a Year's Work in 1 Hour. Here's What That Actually Means.

4 min

A Principal Engineer at Google used Claude Code to reproduce a year of distributed systems work in an hour. The implications go beyond AI hype.

#ai#development#tools

Linus Torvalds is Vibe Coding Now. Yes, That Linus Torvalds.

5 min

The creator of Linux and Git just admitted to vibe coding a Python script. His approach is worth stealing.

#ai#development#tools

Ship Code While You Sleep: The Ralph Wiggum Technique

7 min

An Anthropic plugin named after a Simpsons character lets Claude Code iterate autonomously until the job is done. Here's how it works.

#ai#tools#development

Weekend Project: Build a Security Tool for Your Own Job

7 min

Half of security ops is wrestling with data formats and one-off scripts. Here's how I've been vibe coding tools that actually fit my workflow.

#security#ai#tools#development

Ollama Launch: Run AI Coding Assistants Locally in 30 Seconds

4 min

Ollama's new launch command makes it trivially easy to experiment with AI coding assistants. Here's why that matters and what to watch out for.

#ai#tools#development#security

780 AI Assistants Are Leaking API Keys Right Now. Yours Might Be One of Them.

6 min

The viral AI assistant Moltbot has 60,000 GitHub stars and hundreds of exposed instances leaking credentials to the public internet.

#security#ai#agents

Claude Code Does More Than You Think. Here Are 9 Ways I Use It.

4 min

How I use Claude Code across different workflows, from quick scripts to complex refactors.

#ai#tools#development

I Ship AI in Regulated Environments. Here's How Nothing Breaks.

2 min

How to move fast with AI systems when compliance, audit trails, and risk management are non-negotiable.

#ai#security#compliance

Stop Gatekeeping AI. Build Guardrails Instead.

2 min

Why self-service security with guardrails beats centralized approval for AI systems.

#security#ai#culture

Your AI Security Playbook Won't Survive Production. Here's What Will.

2 min

The gap between AI security frameworks on paper and what actually works in production systems.

#ai#security