News for hackers. Stuff that matters.
Re:Anti-ChatGPT by kelseyfrog on Saturday October 28, 2023 @06:41PM (#38054083)
Why wouldn't they just predict confidences and then set a threshold?
Re:Anti-ChatGPT by cafeoh on Sunday October 29, 2023 @01:48PM (#38060919)
A more political piece of media isn't necessarily less honest or more manipulative. Similarly, a very supposedly "neutral, both-sides" opinion can be very manipulative. The best thing you might be able to do is filter out specific hand-picked subjects (like other commenters said QAnon or specific conspiracies), but I doubt you need more than basic keyword matching for that. Anything further feels to me like you're just tightening an echo-chamber.
Re:Anti-ChatGPT by kelseyfrog on Sunday October 29, 2023 @11:17PM (#38065311)
Your point was that everything would be identified by such a filter.

But if the filter simply predicting an amount then the user could adjust their threshold so that not everything would be blocked. It's a pretty easy fix.

Was your point rather that everything has a political angle?