But what if the user asks Alexa about some topic on e.g. Wikipedia? Should Alexa store the entire web upfront? At some point it might need to send a request of some sort to a server.
(The best counterargument I can think of is that the speech recognizer might be too computationally expensive to run on cheap hardware.)
In other cases those personal assistants could first ask permission to query an API or search engine.
That's a non-trivial modification, even before talking about the processor upgrades required to actually utilize that information and do local processing.
Your suggestion would drive the cost of an Echo from $30 to $300.