-
Why You Need a Thinking Partner (like this Genius)
You may not have heard of him, but James Clerk Maxwell wrote down what we now think of as four equations that define ALL of electromagnetics. You can get a T-Shirt with them emblazoned on it. If you want to know how radio waves propagate, or how a radio functions, or how anything running on electricity…
-
A change of perspective is worth 80 IQ points
We’ve all done it–struggled over some problem until a frustrating end of the day. But after “sleeping on it” and stepping into a hot shower, a breakthrough idea pops up, as if out of nowhere. This often comes from getting too close to the problem. A little distance can make a decisive difference. The quotation…
-
3 Things You Learn Writing Your First Software
AI is getting capable. Software is increasingly being written by smart non-engineers. Here’s a few things that surprise makers when they get into a serious software effort for the first time: Getting it to work once is not the same as building software An easy with with AI feels magical: you describe something, hit enter,…
-
Free training: Architect Like a Surgeon
A free 3-part training series offers career-changing guidance for developers and software architects
-
Vibe Coding Live Experience Lab
See what happens when AI starts implementing your ideas — and why it matters with this live instructor-led experience.
-
Free July Workshop: Developer Career Advice
100% free and available only during July: a video series covering modern career advice for developers. Update: This is closed. Subscribe for future workshops and events. Is the usual career advice for developers obsolete? Yeah, AI is changing everything, and usually not for the better. Your host M.Joel applies his three decades of developer mentoring…
-
🐱 Using Cat Pics to Explain a Surprising LLM Pitfall
One of the several mysteries about the workings of Large Language Models is their unexpected sensitivity to what seems like small changes in prompting. As a result there are many different guides and acronym-laden frameworks for writing effective prompts — including one from me! Writing a good prompt really makes a huge difference between a…
-
AI Code Generation entrenches your software architecture — for better or worse!
I had an odd thought recently. My goal, as a consultant, is to get myself replaced by AI. Let me explain, All AI technology is based on pattern recognition, and the newer models are getting really good at picking up on deep and subtle patterns that are not at all obvious. So when engineers use…
-
FREE Webinar: Amplify Impact as a Software Leader (Final Replay)
Due to popular demand, I’m offering a replay of free live training over Zoom. Sign up here and for email reminders and meeting invitations. Final Session: December 4 @ Noon Pacific / 3:00PM Eastern / Find your local timehttps://us06web.zoom.us/j/86537091325?pwd=Ks3MSNpG279BN1dj5nNQksg08HwzdL.1 Meeting ID: 865 3709 1325Passcode: 162385 Target audience: current and aspiring software architects and leaders. (though…
-
Can AI replace me yet? A software engineering experiment
On my discussion list, I’ll be spending several weeks playing with AI to generate real-world software projects–not a toy but a full-scale project with complexity, testing, and lots of decision points. For this project, I’m choosing to implement invisible XML, or ixml. (Wait, don’t leave! I understand that XML is a sore point for many…
-
A brief but powerful GPT-o1 example
Try this one. I’m rendering the prompt in fixed text so it’s more obvious to human readers. Other LLMs like Google Gemini or even GPT 4o can’t get this. The o1 model nails it, and explains the reasoning.
-
A remarkable conversation with GPT-o1 preview
I had the following conversation with the preview o1 chatbot from OpenAI while I was watching this video, which tackles the opening question. Check out the video for yourself. Props to the video creator Mihai Nica and Grant Sanderson of 3Blue1Brown for the original problem. In the actual AI conversation, the LaTeX was correctly rendered,…