本地端股權研究,LLM 永不產生數值;問題編譯為 Python 指標的型別計畫,模型僅敘述未計算的結果,且每項主張皆重新驗證。
AI 翻譯
Local-first equity research where the LLM never produces a number. Questions compile to a typed plan of Python metrics; the model only narrates results it did not compute, and every claim is re-verifi
金融Python · TypeScriptGitHub @karanmjpinto上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
尚未偵測到更新。GitHub 發布版本後會顯示在這裡。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證本地端股權研究,LLM 永不產生數值。問題會編譯成 Python 指標的型別計畫;模型僅敘述其未計算的結果,且每項主張皆會對照凍結快照重新驗證。
AI 翻譯
Local-first equity research where the LLM never produces a number. Questions compile to a typed plan of Python metrics; the model only narrates results it did not compute, and every claim is re-verified against a frozen snapshot.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Local-first equity research where the language model never produces a number.
-orange.svg)
To make AI-generated investment research checkable.
The goal is not a smarter model. It is a harness around the model good enough that its
output can be checked, repeated and argued with — so when an answer is wrong you can see
which part was wrong, and fix the method rather than the number.
Four commitments follow from that. They are enforced in code, not asserted in a
document, and they are what to hold this project to:檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Local-first equity research where the language model never produces a number.
-orange.svg)
To make AI-generated investment research checkable.
The goal is not a smarter model. It is a harness around the model good enough that its
output can be checked, repeated and argued with — so when an answer is wrong you can see
which part was wrong, and fix the method rather than the number.
Four commitments follow from that. They are enforced in code, not asserted in a
document, and they are what to hold this project to:檢視完整 README ↗