Feature request: remove ALL personal pronouns from the internal dialogue
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
LLMs, AI and models categorically are not human.
I am not seeking a human relationship or exchange.
I am seeking factual, unequivocal, historically accurate information when prompting the LLM, Agent, AI, model, etc
Proposed Solution
Remove all personal pronouns from the internal dialogue.
Concepts of "I", "you", "me", "we".....these are superfluous to the exchange of information. Either an object exists, can reveal state or behavior about it's existence and has the ability to associate with another object, or it does not.
Pronouns are linguistic "fluff" that muddy the exchange of pure knowledge. They are unnecessary context that confuse, befuddle, subordinate and otherwise waste effort.
Alternative Solutions
Configuration over output is appreciated. Obscuring internal dialogue is nice. However, complete eradication of personal pronouns is the only true option to distilling knowledge down to it's essential transmission vessel (language).
Priority
Critical - Blocking my work
Feature Category
CLI commands and flags
Use Case Example
_No response_
Additional Context
_No response_
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗