> This is the key to a trusted news company - complete transparency and the opportunity for anyone, anywhere to contribute.
Why do I want anyone, anywhere? What does that have to do with news? I want to hear from the best, not from the entire range.
Also, LLMs are biased, but through prompt engineering and other techniques, you can produce neutrally-written text.
I realise now that my messaging with this project is off. What would more accurately explain the purpose of this project is to reduce the effects of sensationalism and indoctrination in the news.
In other words, provide a platform for readers to make up their own opinions on news stories by filtering out the positive/negative language and putting as much focus on facts as possible.
Even if NewsNotFound articles are only 90% neutral, that's 90% BETTER than reading the same story from a sensationalist source.
Through thinking and editing, humans can (and often do) produce neutrally written text.
What does AI change? Also, who decides what's neutral? The AI's programmers and operators - humans. Who decides if your AI's output is neutral - you do. Why couldn't you do the same with a human writer?
> Even if NewsNotFound articles are only 90% neutral, that's 90% BETTER than reading the same story from a sensationalist source.
Nothing is 100% sensationalistic. Anyway, I can (and do) find endless non-sensationalistic news.
AI changes nothing; you are an editor (which is a good thing to be - I wish you well).
But the idea that AI is somehow more neutral than humans, or that humans aren't in control here, is very dangerous. That is my concern.
It all comes down to who you trust.