

They do this by running a script/app that sends the user’s comment history to OpenAI with the question “analyze this content for evidence of specific political ideology sentiment.
To me the problem is what they are looking for not how they are doing it. Thought experiment: in what way would it be qualitatively different if they hired a team of people in Upper Elbonia to do the same thing?






I’ve had it fail (ie, stay on and deplete the battery) often enough over the years that I just suspend/hibernate manually before closure.