daveshap
commented
1 year ago As long as the metadata is natural language, no reason not to
On Thu, Sep 28, 2023, 2:28 PM Romans Pokrovskis @.***> wrote:
By design, The ACE framework relies heavily on natural language processing to communicate between layers.
While NLP makes the system human-readable and aligns well with the idea of cognitive entities, it also introduces the possibility of ambiguity, misunderstandings, or misalignments due to the complexities inherent in natural language.
Different models may interpret the same sentence differently, and the 'constitution' passed down through the layers could contain principles that are vague or contradictory when reinterpreted.
Have you considered implementing structured logging alongside free-text responses? This could serve multiple purposes:
-
Enhanced Monitoring: Structured logs could provide a more granular view into the system's state, making debugging and monitoring easier.
Plugin Points for Tooling: The metadata could serve as plugin points for both internal and external tools, offering hints on environmental states, additional capabilities, and resources.
Disambiguation: The metadata could help in disambiguating natural language instructions, ensuring that all layers have a uniform understanding of directives.
— Reply to this email directly, view it on GitHub https://github.com/daveshap/ACE_Framework/issues/53, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACRYW4PPQXUYWB533BQYU7DX4W6VFANCNFSM6AAAAAA5LME3L4 . You are receiving this because you are subscribed to this thread.Message ID: @.***>
By design, The ACE framework relies heavily on natural language processing to communicate between layers.
While NLP makes the system human-readable and aligns well with the idea of cognitive entities, it also introduces the possibility of ambiguity, misunderstandings, or misalignments due to the complexities inherent in natural language.
Different models may interpret the same sentence differently, and the 'constitution' passed down through the layers could contain principles that are vague or contradictory when reinterpreted.
Have you considered implementing structured logging alongside free-text responses? This could serve multiple purposes:
Enhanced Monitoring: Structured logs could provide a more granular view into the system's state, making debugging and monitoring easier.
Plugin Points for Tooling: The metadata could serve as plugin points for both internal and external tools, offering hints on environmental states, additional capabilities, and resources.
Disambiguation: The metadata could help in disambiguating natural language instructions, ensuring that all layers have a uniform understanding of directives.