I use embeddings to create suggestions on what to read when it comes to blogs and articles. It semantically matches articles from sites I provide (like HN of course) against previous things I have read and a set of topics/themes I am interested in. It does this periodically and provides a suggested list of what to read next. Implemented this a few weeks ago and its throwing up pieces I might have otherwise missed.

I am however concious that sometimes the most interesting things in a given day are not related to anything else I am reading or would read - this is what I get through scrolling through HN serveral times a day.