When I worked with the HN post data, I noticed that some years ago HN users had correctly predicted the "Show HN" projects that later got funding. Those projects had more upvotes. The more recent data has no such connection. It seems that the influx of users reduced the quality of judgement. So one way to improve HN submissions and comments is to weight points by the user's tenure on HN. I also suspect that early com…
Another factor might be the abuse of the bookmark feature. I tend to upvote stories that seem interesting when I am at a hurry just as a way to save them in the upvoted stories section for a later time. About the comments, pretty sure the sorting algorithm still takes into account a user's avg score. I usually make late comments but they show up well above other threads.
Otoh, I often bookmark an article just to keep a reference to the comments.