Jev 從 182 個 Hermes skill 裡最多選一個

作者: TypeSafe

函式呼叫

TypeSafe

TypeSafe cookbook

分類這個使用案例

  • Function calling0.86
  • Shipped0.92
  • Measured0.78
  • Usefulness0.26
  • Cookbook1.00
  • Ready0.95
  • Specific case0.44
  • Copy quality0.67
  • Creativity0.72
  • Distinct intent0.74
結果
從 182 個 skill 的目錄裡,每個回合最多一個 skill 名

問 Jev 這個 Hermes 代理人回合是否需要 skill,再問 182 個名字裡該插入哪一個。

問題

Primitive

Noul

Evaluate how true something is

Name
gate::acts_on_user_system
指示
Is the assistant being asked to act on the user's files, accounts, devices, or online services, rather than only to explain or advise?

Primitive

Noul

Evaluate how true something is

Name
gate::would_follow_documented_procedure
指示
Would a careful expert answering this consult a specific documented procedure or set of commands, rather than answering from general understanding?

Primitive

Noul

Evaluate how true something is

Name
gate::prose_suffices
指示
Could a knowledgeable generalist fully satisfy this request in prose, with no tools, no documentation, and no access to the user's files or accounts?