Hello Everyone!
I am looking for feedback on my newest project - an entirely automated Top Headlines Newsletter, powered by GPT-4. Top news that is picked and written entirely by AI is delivered to your inbox every morning at 9 AM PST.
Our system is fully automated, taking care of everything from selecting topics to sending the newsletter. This means that if I went on vacation, you would still receive a newsletter every morning.
Our newsletter is integrated with our site, and all stories use 2 left, 2 center, and 2 right wing sources (characterized by AllSidesMedia).
I truly think that AI can revolutionize how we consume news, from mitigating polarization, stopping misinformation spread, and minimizing bias. Please let me know your opinions below!
Just because your system is automated doesn’t mean it’s free of bias. LLMs are trained on human-generated content. Human-generated content has biases. The model will reflect those biases. There’s also the proclivity of GPT to be confidently incorrect, like when it made up completely bogus court cases and a credulous lawyer used them in an actual case. I wouldn’t want to get my news from a source that may be lying to my face.
I have bad news for you lol.
But that’s exactly the thing. I don’t get my news from comanies that outright lie. With the LLMs you don’t really know, so it’s not exactly trustworthy either.
And even then, biases are not entirely bad. I often like to say, that I’m biased towards both truth and science.