The Engineering Notebook — page 33 of 35
Notes on building with AI, agents & the modern stack.
Deep dives on AI/ML, RAG systems, agent engineering, and senior-engineer architecture decisions — a new post every week.
AI and Machine Learning Apple's M5 Max Just Made the Case for Local AI Development. NVIDIA Should Pay Attention.
128GB of unified memory at 614 GB/s in a laptop. The M5 Max isn't just a faster chip — it's a completely different approach to running large language models locally.
Frontend and Mobile Google's Desktop Mode for Pixel: Can It Finally Kill the Laptop?
Android 15 brings a real desktop mode to Pixel. After Samsung DeX had a seven-year head start, Google is finally paying attention. Here's what it means.
AI and Machine Learning Why AI Latency Matters More Than Intelligence: The 232ms Lesson From GPT-4o
Everyone's obsessed with making AI smarter. The real breakthrough is making it faster. GPT-4o's 232ms response time changes what AI can actually be.
Technology MWC's Robot Obsession Distracted You From What Actually Matters
Everyone shared the dancing robot videos from MWC 2024. Almost nobody talked about the on-device AI demos that will actually change how you use your phone.
AI and Machine Learning AI Coding Agents Won't Replace You. But They Will Replace How You Think About Code.
Everyone's asking if AI will replace engineers. That's the wrong question. The real shift is in what 'writing code' even means anymore.
Cloud and DevOps Your Cloud Region Is in a War Zone. Now What?
In January 2022, Houthi drones hit targets across the UAE while rumors swirled about a strike near a cloud data center. The cloud has a street address, and that address can be in a war zone.
Breaking Tech News Apple's M4 Chip: 38 Trillion Operations Per Second and What It Actually Means for Developers
Apple's M4 isn't just a faster chip. Its 16-core Neural Engine pushing 38 TOPS is a bet that the future of AI is local, not cloud. And I think they're right.
Breaking Tech News The M5 MacBook Pro: Cutting Through the Spec Sheet for Developers
Apple's M5 MacBook Pro brings Neural Accelerators to every GPU core and up to 128GB unified memory. Here's what that means if you're running local AI models or compiling large codebases.
Technology Ameca Stole the Show at MWC 2024. The Face Is the Product.
At a conference dedicated to mobile tech, the most talked-about thing wasn't a phone. It was a humanoid robot with a face so lifelike it made people genuinely uncomfortable.