Thank you! This is exactly the information the OP seems to have missed. It seems to confirm my suspicion that the author’s concerns about server-side privacy are unfounded — I think:

> The client decrypts the reply to its PNNS query, which may contain multiple candidate landmarks. A specialized, lightweight on-device reranking model then predicts the best candidate…

[please correct me if I missed anything — this used to be my field, but I’ve been disabled for 10 years now, so grain of salt]

The devil is in the proprietary details though.

Sorry, what do you mean by “proprietary details”?

They are alluding to the fact that the implementation is closed source, and therefore "untrustworthy". It's a trite point, of course, but not without some merit.

I don’t see any merit, honestly. That would assume one is able to audit every bit of code they run, including updates, and control the build system.

I mean, the Wally paper contains enough information to effectively implement homomorphic encryption for similar purposes. The field was almost entirely academic ~12 years ago…

I miss talking shop on HN. Comments like that are why we can’t have nice things.

I do agree that everything is politicized. I'd have liked to have seen an explanation for laypeople and perhaps the option being opt-in. To me, there is some merit in that stance. It is a side-note. It is a shame that we can't talk about these things openly without people getting offended because of it.