AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证Make your AI subscriptions (Claude, ChatGPT, Grok, Gemini) debate each other, then judge each other blind. No API keys.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Make your AI subscriptions debate each other, then get one consolidated answer.
Claude, ChatGPT and Grok (and Gemini, if you have it) each answer your question, read each other's
answers, argue, and revise. Then they judge each other blind: every AI scores the others against the
same checklist, and battler turns that into one verdict: the best-supported answer, where they agree,
where they still disagree, and who argued best.
No API keys and no per-token bills. battler drives the official tools you're already signed in to, so
every call uses the subscriptions you already pay for.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Make your AI subscriptions debate each other, then get one consolidated answer.
Claude, ChatGPT and Grok (and Gemini, if you have it) each answer your question, read each other's
answers, argue, and revise. Then they judge each other blind: every AI scores the others against the
same checklist, and battler turns that into one verdict: the best-supported answer, where they agree,
where they still disagree, and who argued best.
No API keys and no per-token bills. battler drives the official tools you're already signed in to, so
every call uses the subscriptions you already pay for.查看完整 README ↗