ai.
14 writings found
Latest Archives
Tests Are the Real Safety Net: Why Your AI Specs Need Executable Validation
Writing specs for LLMs is trendy. But without automated tests, you're flying blind. Here's why the spec document isn't your safety net.
Building macOS Apps Without Knowing Swift: What Vibe Coding Actually Teaches Us
I built two monitoring tools for my M5 MacBook using Claude and GPT without writing Swift myself. The results work, but should they?
Google's Vibe Coding XR: When AI Writes Your Spatial Computing Apps in 60 Seconds
Google Research launches XR Blocks with Gemini integration, letting developers prompt their way into physics-aware WebXR apps. I dig into what this means.
Starlette 1.0 and the Problem of Training Data Obsolescence
Starlette finally hits 1.0, but breaking changes expose a fascinating problem: how do you make LLMs generate code for frameworks they weren't trained on?
Starlette 1.0 and the Problem of Teaching AI New Tricks
Starlette finally hits 1.0, but breaking changes expose a fascinating challenge: how do you get LLMs to generate code for versions they weren't trained on?
Starlette 1.0 and the curious case of teaching AI new tricks
Starlette finally hits 1.0, but what happens when your LLM was trained on outdated code? Claude's new skills feature might just solve that problem.
Automating Security Fixes at Billions-of-Users Scale
How Meta's security team uses AI to patch vulnerabilities across millions of lines of mobile code without driving engineers insane.
Vibe Coding a Mac App in 45 Minutes: What This Says About Development in 2026
Building a custom presentation app overnight shows how AI coding tools are reshaping what's possible for developers willing to explore unfamiliar territory.
Vibe Coding a Mac App in 45 Minutes: What This Says About Software Development in 2026
Building a custom macOS presentation app overnight shows how AI coding tools are reshaping what's possible for developers outside their comfort zones.
Knowledge Priming: Teaching AI Assistants Your Codebase Like You'd Onboard a Human
Stop fighting AI's generic patterns. Treat project context as infrastructure and watch code quality transform through systematic knowledge priming.
Building a Live Documentation Ecosystem for AI Coding Agents
Showboat's new remote streaming feature and companion tools create a real-time feedback loop for AI-assisted development workflows.
The Code Quality Problem AI Agents Won't Tell You About
AI coding agents generate working code fast, but what about internal quality? A real experiment reveals subtle debt patterns that compound over time.
ChatGPT's Secret Container Upgrade: Bash, Package Installs, and Network Downloads
ChatGPT's code execution got a massive upgrade nobody documented. It now runs Bash, installs npm/pip packages, and downloads files. Here's what changed.
AI Coding Agents Are Fast, But They Write Like Junior Developers
I spent months testing AI agents on a real codebase. They shipped features quickly, but the code quality tells a different story about sustainable development.