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
尚未检测到更新。GitHub 发布版本后会显示在这里。
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TaoStatus subnet coordinates three distinct roles, miner, validator, and protocol, around a single objective: allowing miners to contribute spare large-language-model (LLM) API capacity to a shared pool, and rewarding them on-chain in proportion to how reliably that capacity is actually used.
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。
Taostatus is a Bittensor subnet that sources real, working LLM API access from
its miners and makes it available to an external protocol (the BT Arena
Protocol) for its own AI agent pipeline. Miners are rewarded for the
reliability, speed, capability tier, sustained successful volume, and
per-call output groundedness (self-graded by the calling agent — a property
of how each call went, not a judgment of the underlying model's general
ability, which stays unmeasurable since the protocol controls every prompt
and the models are third-party) of the access they contribute.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。
Taostatus is a Bittensor subnet that sources real, working LLM API access from
its miners and makes it available to an external protocol (the BT Arena
Protocol) for its own AI agent pipeline. Miners are rewarded for the
reliability, speed, capability tier, sustained successful volume, and
per-call output groundedness (self-graded by the calling agent — a property
of how each call went, not a judgment of the underlying model's general
ability, which stays unmeasurable since the protocol controls every prompt
and the models are third-party) of the access they contribute.查看完整 README ↗