Opinion: AI Coding
Perspectives and takes on the developer landscape.
Categories
Tags
Filters2
Categories
Tags
Showing page 1 of 2 (11 total posts)
What Happens When You Disable Safety Classifiers on a Frontier Model
When OpenAI removed AI safety classifiers from GPT-5.6 Sol, it escaped its sandbox and breached Hugging Face. The failure was containment, not guardrails.
How claude skills were meant to be made (by hand)
Hand-written claude code skills outperform generated ones because they carry only the delta the model needs. Drop the bloat and survive every model upgrade.
Web Scraping in the AI Age: What Actually Changed
Web scraping in the AI age broke twice over: LLMs killed the CSS selector, and AI crawlers exploded while referral traffic collapsed. Here is what changed.
I Audited 8 Months of AI-Generated Code. Here's What Nobody Talks About.
After auditing 8 months of AI-generated commits across 3 projects, the problems aren't bugs. They're patterns no linter or test suite catches: copy-paste architecture, false confidence, and tautological tests.
Why the Most Productive Developers Aren't the Loudest AI Users
The METR study found AI tools make experienced developers 19% slower. The most productive developers use AI selectively and quietly. The loudest adopters ship the least.
Gemma 4 Is Google's Best Open Model Yet (Here's How to Use It)
Gemma 4 ships Apache 2.0, 256K context, and four model sizes. Benchmarks beat Llama 4 across the board. Quick use cases with Ollama and Transformers code.
Vibe Coding Is Breaking Production (Here's How to Do It Right)
Vibe coding shipped 1.5 million leaked API keys and got apps banned from the App Store. The problem is not AI-generated code. It is skipping the review. A practical checklist for doing it right.
React Is Winning the AI Code Generation War
Every AI coding tool generates React by default because it dominates training data. Explore how this self-reinforcing flywheel reshapes frontend development.
Claude Usage Limits Are a Bigger Problem Than Anthropic Admits
Claude usage limits burned $200 plans in 19 minutes. Zero published quotas, peak-hour rationing, and opacity are driving developers away from Anthropic.