Software development jobs grew 10% over the last year while the overall market declined 5.8%. Quite the narrative violation.

This AI agent bankrupted its owner. He asked it to join an online community to gather some info. It ended up burning $6k in AWS credits. The worst of two worlds: overpriced cloud platforms, and overeager AI agents. Best to stay away from both.

We're looking for people to betatest a new course on agentic engineering. LMK if you're interested in checking it out! Interested in feedback from both technical, semi-technical and even completely non-technical people. Send me a DM if you'd like a link!

Just tried Fable. It burned 1.3M tokens in 7 minutes. Thats $160 per hour. Equivalent to a $333k/year salary 😵‍💫

F grades in computer science at UC Berkeley have more than TRIPLED in two years. From less than 10% to over 35%. The next generation of software engineers will be the least skilled ever.

guys i’ve found the ultimate ai orchestration setup. parallelized claude codex with a cross-functional agentic terminal plus 4x stochastic idle-time apps to train my probabilistic thinking while the agents work. never felt smarter or more productive

Light-mode just arrived to Scrimba. Hope you like it!

The Udemyfication of coding agents has begun.

I just created a sidebar Dock for MacOS, and it feels amazing to use. Every app has a vertical sidebar these days, why doesn't the OS itself have it?

The secret MacOS API that Codex use for their new impressive computer-use feature. Codex can run several computer-use tasks in parallel, which shouldn't really be possible. Most tools in this space take over your mouse and keyboard completely, so you can't use your machine while they work. Codex doesn't do that. The team at Software Applications Inc. figured out how to avoid it. (That's Sky, by the way, former Shortcuts people Apple acquired a while back.) I wanted to know how they pulled it off. So I did some digging. Here's what I found. The "secret API" is AXUIElement, macOS's accessibility framework. Apple built it for VoiceOver. The Codex team just repurposed it for LLMs. On the reading side: the AX Tree. No screenshots. No OCR. Codex reads the accessibility hierarchy directly. Every button, text field, and menu item is already labeled and structured. It's basically a DOM equivalent that Apple built decades ago for assistive tech. That's what the model actually sees. On the writing side: events go through accessibility APIs, not CGEvent. Clicks hit the target element directly, never through the shared system cursor. Those virtual cursors you see wiggling around? Purely cosmetic. That's why focus doesn't get stolen. That's why N agents can run at the same time without stepping on each other. It doesn't work on Windows, so there they hijack the cursor. The Sky team didn't actually invent this approach. UI Browser was using the same APIs years ago. I found hacks like this super-cool, and hope more people build cool shit with it.

We just crossed two million users on Scrimba. Thank you so much to every single one of you!

Software development roles grew 15% over the last year while the overall job market declined 5%. That’s a 20% gap, up from 16% a month ago. What a narrative violation.

The world’s demand for software is far from saturated.

LLM coding benchmarks collapse from 90% to 4% the moment you give them a language they haven’t memorized 📉 This indicates that LLMs alone lack a fundamental part of intelligence. If a human learns to write FizzBuzz in Python, they’ll easily be able to transfer that over to Java as soon as they’ve learned Java’s syntax. LLMs, not so much. To reveal this, the authors picked obscure programming languages where they knew the training data was extremely limited, like Brainfuck and Shakespeare. The LLMs were given all the documentation they needed to understand the syntax of the languages. But even with full docs, they couldn’t “reason” their way to a solution. None of the models managed to solve any of the hard problems. These were SOTA models at the time of writing the paper: GPT 5.2, Gemini 3, etc. This makes me think that LLMs lean just as much into memorization as reasoning when they help us solve problems. For many use cases, that’s not a problem in itself. But I don’t think we’re at AGI or ASI level yet.

Bookkeeping is the worst. Here's how to automate it with Claude Cowork.