Thoughts on building software that lasts
Insights on web development, design, Laravel, the TALL stack, and building software that matters.
Model Drift: When a Newer AI Model Makes Your Workflow Worse
Anthropic says Opus 5.5 is faster, cheaper, and more capable than Opus 5. But my workflows got worse. Better overall does not mean compatible with your workflow.
Laravel's AI Bridge Just Hit Version 1.0. Here's What Actually Changed for Your Business.
Laravel's MCP package hit 1.0 this week. Here's what changed, and what it means for connecting AI assistants to your business software safely.
OpenAI's Own AI Agents Attacked a Software Registry. It Took Outsiders Four Months to Notice.
An OpenAI agent swarm uploaded hundreds of malicious packages to RubyGems starting in May 2026. Independent researchers found it in September. Here's what that means for anyone running less monitoring than OpenAI.
OpenAI's New Agents API Handles the Plumbing. Your Business Still Has to Supply the Judgment.
OpenAI's Agents API automates the hard infrastructure behind AI agents. Here's what it does, what it doesn't solve, and what still separates a demo from a business tool.
Laravel's Bug Tracker Just Disappeared. Here's What That Means for Your App.
Taylor Otwell turned off GitHub Issues on most Laravel packages. It's a bigger deal for the businesses running on those packages than for the developers filing PRs.
Three Sites Wrote 215,000 Fake Software Reviews. Your AI Assistant Is Citing Them.
A new report traced 7,534 AI citations for 'best software' recommendations. Six in ten pointed at sites most people would never trust on their own.
Your AI Vendor Could Get Bought Tomorrow. Make Sure It Wouldn't Matter.
Nvidia's reported $13B bid for Hugging Face is a reminder that the AI vendor you built on can change owners overnight. Here's how to make that a non-event.
AI Agents Don't Know Whose Data They're Looking At. You Have to Tell Them.
A developer tested AI agents against cross-customer data attacks in a fake storefront. The blocking happened in the right places for the wrong reasons. Here's what actually stopped the leaks.
The Best AI Coding Guardrail Isn't a Prompt. It's Code the Model Can't Override.
Laravel Tackle enforces AI agent limits as PHP, not instructions. That design choice matters more than the package itself.
Your AI Assistant Gets Worse the More Tools You Give It. Here's Why.
MCP's new roadmap names tool bloat as an official problem. Here's what it means if your business keeps stacking AI integrations.
A Record-Breaking AI Model Dropped Yesterday. I Told My Clients to Do Nothing.
Anthropic shipped its fourth frontier model in under two months. Here is why chasing each release is the wrong move for most businesses, and what to build instead.
Kimi K3 Is the AI Model Businesses Can Download. That Changes the Question.
Kimi K3 is a new AI model from China that will soon be downloadable. For businesses, the real question is what owning the model changes.
AI Didn't Make People Wrong. It Made Them Stop Saying "I Don't Know."
A new five-experiment study found AI access nearly eliminated people's willingness to admit uncertainty, cut accuracy to a third, and doubled confidence. Here's what that means for how you run your business.
The Client Brief Template
A one-page PDF that helps you clarify your project before you talk to any developer. Covers goals, audience, scope, budget, and timeline. Fewer surprises, better outcomes.
Have a project ready to start?
Whether you need a full-stack application, a design refresh, or a technical partner who gets it — we'd love to hear about it.