I use AI for 99% of my code now and I'm not going back. But I'm seeing a lot of posts saying you don't need to read the code at all, and I don't think that scales or applies to everything. For apps with few users, no PII, payments, or health data its probably fine. I vibe code all kinds of stuff without reading a single line. But that changes once a bug can cost someone money, their data, or their health. My review effort scales with blast radius. Automate everything, then put human eyes where mistakes have real consequences. Does that mean I review every line? No. It means guardrails, deterministic checks, meaningful tests, and spot checks on PRs that touch PII, payments, security, and compliance. I'll go in more detail in the new series I'm working on.

Crazy to think about that even after 5 years people find these videos helpful, especially in today's reality with AI. Also it's only been 5 years but with how fast we're advancing it feels like this was more than a decade ago.

Docker sandboxes are pretty cool. Covering this as the first step of setting up agentic workflow to build an app in my series. Should I call my series "Vibe the right way"? 🫣

I'm planning a 3 part series where I build a budgeting app for myself. Not a product, just the features I actually need, built with AI agents inside guardrails so they don't do something silly. Part 1 is gonna be the intro & planning. Part 2 is about the architecture, ADRs, specs, setup, skills, guardrails, so the agents have the reasoning and follow rules/patterns. Part 3 is the build, using the Threejs, React, Inertia, Laravel with AI SDK, MCP, Reverb, Boost and other good stuff. I'm more excited about part 2 because that's where I spend most of my time day to day at work. Miss making videos. I've lost some of the motivation over time and I'm hoping to find the free time, and the thrill, to do it again.

"You need a better harness"

Asked Claude to /grill me. It said "medium or well done" 😒

Quick tip, something I had to do recently. Claude Code keeps its own auto memory besides CLAUDEmd. Notes it saves for itself per project, loaded into new sessions automatically. Usually helpful. But when I want a second unbiased opinion, or when an earlier debugging guess was wrong, it kept giving me the same answer. Clearing the memory for that project from stale or wrong items gave me much better output.

Wife texts me a shopping list. I paste it into Claude and get back an artifact with the list, plus features like add/remove items, check them off, categorized by aisle, etc. Claude takes < 90 seconds to build. I could've just used the list as is or downloaded an existing software. But why, when Claude can whip up a mini app on demand, built exactly how I want it, in less time than it would take to download & set one up.

I tend to use "duuude, r u serious?" and "tldr please" quite alot when chatting with Claude. Saw a recent skill called "/bro" and it's funny how accurate it is.

Someone shared with me that they're having a hard time finding PHP/Laravel jobs. My advice was first to review and edit the resume. Instead of focusing on frameworks and tools, focus on what you actually shipped and what changed because of it, and then search for jobs based on that, not on the stack. The outcomes you've delivered translate way further than the framework you delivered them in. On the flip side though, I do think more PHP/Laravel jobs will open up in the near future. As AI adoption grows, people are gonna realize how fast you can build stuff with Laravel

Thinking of building some cool tooling with Laravel AI for myself & can record the process. Would you rather watch 30+ video of the decision making and setting up guard rails to let AI build itself or prefer short summary <15 min video walkthrough?

This is concerning. @TeamYouTube not cool to treat content creators like this. At least share what exact line or segment from video violated which policy.