Jev が 182 の Hermes スキルから高々一つ選ぶ

作者: TypeSafe

関数呼び出し

TypeSafe

TypeSafe クックブック

このユースケースを分類

  • 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
182 スキルのカタログから、ターンあたり高々一つのスキル名

Hermes エージェントのターンにスキルが要るか、それから 182 のうちどの一つの名を入れるかを Jev に聞く。

質問

プリミティブ

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?

プリミティブ

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?

プリミティブ

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?