Hi, thank you for the feedback. I should have added that we launched it yesterday so it there is still some quirks. Yes, we use language models to do the summaries, they are not perfect yet and the feed ordering also needs to be improved.

Since you get the actual news headlines and teaser on the detail, we assume some inaccuracies are ok for now. The primary focus right now is clustering and a high-level overview over the news landscape. Especially to get perspectives about an event from many different sources.

We are iterating quickly and expect this to somewhat stable and reliable by mid April.

Would appreciate if you had a look back again then to share your feedback.