Show HN: 40M embeddings to find who knows what on HN (blog.wilsonl.in)

Nicely done. I was able to see my tiny contribution to HN clearly.

Few questions:

1. Did you create embeddings for the whole comment or you used chunking?

2. How do you determine the effective keywords in comments?

TIL

"Grill Cleaning Techniques and Tools* is among my full zoom-out expertises.

AMA.

This worked really well for clickhouse and sqlite. Any plans to open source?

Text selection doesn't work, and I can't navigate to the user's news.ycombinator.com profile; otherwise, it's neat.

Interesting

This is an interesting tool, but I'm not sure how to use the information it gives me. If I end up with a list of users who are interested in the same topic, what's the preferred way to use this new found info?

I don't want to just start cold emailing strangers.