without sacrificing your privacy

Pls explain:

We also receive the following information from third parties when you use the Service:

Inputs and Outputs. When you use the Service to summarize or query web content, we automatically receive a payload back from the relevant [Third-Party Models] containing the contents of your query; information about the model queried (such as the name and version number); information about technical problems with processing the query, if any; the number of tokens required to process the query; and the model Outputs in response to the query. We do not store this data beyond temporarily caching it to process your query and return the Outputs to you.

I will not be willingly adding any AI.

They should launch it into orbit.