Mainstream AI coding harnesses are now interchangeable for daily dev, except Google Antigravity

鸭哥的观察：为什么现在的 AI 编码 Harness 已经切换无感了？

Yage's hands-on comparison finds Cursor, Codex, Claude Code, and OpenCode have converged into near-identical daily coding experiences for 95% of CRUD tasks. Model smarts and feature checklists are saturated, making them interchangeable. Claude Code's exclusive Agent Teams and Dynamic Workflows are undercut by flaky Remote connections, aggressive safety filters that misfire, and server-side stealth downgrades. Google Antigravity is the sole outlier: Gemini's internal thinking budget consumes max_output_tokens and truncates long code generation, the desktop client and IDE plugin freeze often, and its product line is split across five confusing components with SSH still locked to Linux hosts only. Tool choice now hinges on workflow preference, not raw intelligence.

Why it matters: Yage's comparison has a concrete feature matrix and hands-on model experience, not empty talk. The '95% interchangeable' conclusion is directly useful for practitioners, hitting all three HKR axes. Deduction because it's a personal blog without third-party data, and the Claude...