NerfWatch()
Track AI degradation with daily tests and community votes
- Track AI model performance daily to detect degradation early.
- Community votes flag when a model’s output drops below its initial week’s level.
- Comparing each model only to its own first week provides a consistent baseline.
Daily tests and community votes on whether AI models got nerfed. Each model is only ever compared with its own first week.
Visit NerfWatch()
More in Dev Tools
- cc-switch — A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,…
- ai-goofish-monitor — 基于 Playwright 和AI实现的闲鱼多任务实时/定时监控与智能分析系统，配备了功能完善的后台管理UI。帮助用户从闲鱼海量商品中，找到心仪产品。
- medusa — The world's most flexible commerce platform for agents and developers
- ccstatusline — 🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support,…
- Skill_Seekers — Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with…
- modly — Desktop app to generate 3D models from images or prompt using local AI — runs entirely…
- go-stock — 🦄🦄🦄AI赋能股票分析：AI加持的股票分析/选股工具。股票行情获取，AI热点资讯分析，AI资金/财务分析，涨跌报警推送。支持A股，港股，美股。支持市场整体/个股情绪分析，AI辅助…
- Fusor — Like Vue, but the logic is Rust
Opening Liz…
