|
Hey Reader, It's been two months since I updated the list, so let's quickly take a look at what's new. A little context: it has been significantly simplified. I really only use GPT-5.3 Codex High and Extra High (Fast if in Cursor) for almost everything. It requires you to be a little more aware of your prompting and your goals, and to ask the right questions. But it is the smartest AI model, and it is not even close. There's a huge shift in the industry right now, with people switching away from Claude Code towards GPT-5. No surprise there. That said, Claude Opus 4.6 (Thinking) is still a really good model that I use every single day. When people like me say one model is better than the other, that is true . But it doesn't mean the other models are bad. It's like comparing a Ferrari to a Lamborghini. Both are really expensive, desirable cars that do way more than what they need to get the job done. I use Opus 4.6 mostly for design, small changes, quicker experiments, and an increasing amount of agentic tasks. For example, I ask Claude Code to convert images or videos, to summarize or translate things, to research. It has almost replaced me using Claude on the web (with the exception of Projects, which I still use on the web). Finally, Gemini 3 Flash has completely replaced Sonnet and Opus in my apps. For example, my Prompt Coach is running on it for free queries. Gemini 3 Flash follows instructions really well. It is extremely fast compared to Sonnet and Opus, and it is extraordinarily cheap, which makes it great for things like lead magnets. Literally ignore everything else.
Ignore all of it. And as always, if you prefer to use Claude over GPT-5, then do it. Don't let me discourage you. The most important thing you can do is execute. Do not min-max. Execute. Because opportunities are endless right now. Go build! Speak soon, |
Coder of 20+ years teaching non-technical people how to build their own software business in 30 days with AI. No devs or code required.
Hey Reader, Anthropic just announced free monthly API credits for all Claude subscribers! 🎉 Sounds great, right? Well, let's read the fine print... The catch nobody's talking about. Starting June 15th, third-party tools like Conductor can no longer tap into your Claude subscription directly. Instead, they will now pull from those shiny new API credits. But here's the thing. If you're on the $100/month Max plan, you get $100 in API credits. Claude Opus 4.7 will chew through that in a few...
Hey Reader, This is not our regular scheduled programming. If you're old enough to remember the ILOVEYOU virus from 2000s, this will feel familiar. Back then, one email worm hit 10% of every computer connected to the internet. It caused $10 billion in damage. All because people clicked one email attachment. That was 26 years ago, and this week it's kinda happening again. The new virus doesn't need you to click. A group just compromised hundreds of packages across coding ecosystem. Think of...
Hey Reader, It's May 2026. People keep asking what I'm actually using to ship apps right now. Not what's trending on X. Not what some sponsored influencer says. What's in MY toolkit, every single day. So here's the full stack. Steal it. Cursor is the cleanest coder out there. The v3 release is genuinely insane. Best AI coding tool I've ever used. Best overall design and UX. But my Cursor usage exceeds $2-3k/mo and it's not cheap. In fact, the last 30 days were particularly heavy... I use it...