code generation
3 published articles
Benchmark Analysis
HumanEval Measured Whether AI Could Code. It Never Asked Whether the Code Was Real Work
HumanEval's 164 function-completion problems became the standard test for AI coding ability, but memorization and its narrow scope left a wide gap between passing the benchmark and handling a real codebase, a gap SWE-bench was built to expose.
2026-07-30
AI IDEs
Cursor 2.0 just asked the question every developer was avoiding: do you still want to type?
Cursor 2.0 introduces a purpose-built interface and the Composer model, designed to work with AI agents rather than alongside a human typist. This review breaks down what changed, how it performs, and why it may redefine the developer’s role. The question it asks: do you still want to type?
2026-07-15
Multi-agent architectures
Why Qoder gives every AI agent a boss
Qoder's Experts Mode replaces peer-to-peer multi-agent messaging with a single Leader that coordinates specialized experts asynchronously. The architecture reduces state explosion, improves quality across four dimensions, and extracts reusable skills after each task.
2026-03-11