Skip to main content
← Back to Blog

Developer Experience

4 articles

A desktop workstation running a local LLM for coding — 80 billion parameters, 3 billion active — representing the shift from cloud AI to local AI coding
AI & Developer Experience •

The Local LLM Coding Revolution Just Started — 80B Parameters on Your Desktop, 3B Active, Zero Cloud Bills

A tech journalist just declared he finally found a local LLM he wants to use for real coding work. Qwen3-Coder-Next runs 80 billion parameters on a desktop, activates only 3 billion per token, and plugs directly into Claude Code. The cloud-only era of AI coding is ending. Here is the full technical breakdown, the privacy argument nobody is making, and why this changes the economics of AI-assisted development.

18 min read
Read more →
Three AI coding agents — database, security, and test — sitting at terminal screens writing and reviewing code, all guided by a central SPEC.md specification document
AI & Developer Experience •

The $300K Bug That Was Never the AI's Fault — Inside Addy Osmani's Spec Framework That Changes Everything

Google Chrome's Addy Osmani just published the definitive guide to writing specs for AI coding agents on O'Reilly Radar. His 5-principle framework — backed by GitHub's analysis of 2,500+ agent configs and Stanford's 'Curse of Instructions' research — reveals why your 2,000-line prompt fails, what it actually costs, and the exact playbook to fix it.

18 min read
Read more →