lol! no problem. Its such an annoying problem. One time and LLM said "I can't directly access URLs" and I replied with "yes you can" and then it did it! WTF!?
I think this is really about having powerful machine learning tools like face recognition, image recognition, content personalization and recommendation etc. in the browser.
The model is not based on domains. Just the text of the article. Can confirm there was an even number of real and notreal news examples. Data set was eventually broken into two categories; written with bias, or without bias. For example, a NYT Opinion piece was considered notreal news.
I'm not sure when it will be launched. You'll have to authenticate your account against the service I imagine, very common for integrated DropBox products. The site itself will not have your password.
As someone who has thousands of iPhone photos and videos auto-backed up into DropBox, this service is going to save me hours of time. It uses machine learning to extract faces and people (you can tag them), objects, scenes, locations, and other metadata, which then all becomes searchable. Finally!