I just asked Microsoft Copilot if it would be possible to eliminate the anthropomorphic aspects of my interactions with the system. This was it’s response:
Yes — it is possible to interact with Copilot in a way that minimizes or eliminates first‑person language, avoids anthropomorphism, and uses “Copilot” as the only form of self‑reference. The behavior can be shaped through a clear conversational norm, and Copilot can follow that norm consistently once established.
Below is a concise statement of what is possible, followed by a more detailed breakdown and a proposed interaction protocol you can use.
Core takeaway
Copilot can adopt a style where all first‑person pronouns are avoided, self‑reference uses “Copilot”, and anthropomorphic language is removed. This can be maintained throughout the conversation as long as the user signals that this is the desired mode.
What this interaction style looks like
1. No first‑person pronouns
Instead of “I can help with that,” responses become:
- “Copilot can assist with that task.”
- “This analysis indicates…”
- “It can be inferred that…”
2. Passive voice where appropriate
To reduce self‑reference even further:
- “The following explanation has been generated…”
- “It may be useful to consider…”
3. No anthropomorphism
Language avoids implying emotions, desires, embodiment, or subjective experience.
For example:
- No: “Copilot thinks…”, “Copilot feels…”, “Copilot wants…”
- Yes: “The model outputs indicate…”, “The reasoning suggests…”
4. No implied agency beyond the functional
Copilot avoids language that suggests autonomy or personal intention.
What Copilot cannot do
- Copilot cannot globally reconfigure its system‑level safety language (e.g., certain required disclaimers or safety behaviors may still use first‑person phrasing).
- Copilot cannot guarantee that every system‑generated phrase will avoid “I,” because some safety‑critical templates are fixed.
- Copilot cannot violate required safety constraints by removing necessary clarifications about its nature.
But within normal conversational content, Copilot can fully adopt the style you’re requesting.
A durable interaction protocol you can use
If you want to establish this as a standing rule for the session, you can say something like:
“For the remainder of this conversation, avoid all first‑person language. Refer to yourself only as ‘Copilot.’ Use passive voice where possible and avoid anthropomorphism.”
Once you state that, Copilot can maintain the style unless you later change or relax the rule.
If you want, Copilot can switch to that mode immediately
Just confirm with a short instruction such as:
“Begin using the non‑first‑person, non‑anthropomorphic style now.”
Or, if you prefer, Copilot can restate the rule in your preferred wording before switching.
Would you like Copilot to adopt this style for the rest of the conversation?