[mlucy]

:P

For what it's worth, people are doing job candidate clustering anyway right now. It's just that most people are doing it with keyword search or something.

Doing it with embeddings instead would probably increase the quality of the clustering at the cost of some interpretability. (i.e. you wouldn't be able to say "We didn't show your resume to this employer because it didn't contain both the word "Java" and the word "Agile", but maybe that's a good thing).

It's sort of a hard philosophical question how much you care about transparency/interpretability vs. quality, especially for socially important tasks like hiring.

[wutbrodo]

Right, it's a little absurd to complain about flaws in a potential hiring filter without realizing how incredibly flawed current hiring is, relative to some unrealized ideal.

[sgt101]

Respectfully I disagree, if something is bad then the fact that the other thing might be bad doesn't make it ok. Either be demonstrably better (this isn't) or stop.

[wutbrodo]

The solution does claim to be better along some axes; your statement would seem to imply that you can't work towards a solution to any problem until all of them are solved. That seems like a recipe for never improving anything, no?

It would be like complaining about an agricultural innovation that's projected to reduce starvation, because it doesn't also cure diabetes. I wouldn't want such progress to "just stop" because they're leaving a given problem unsolved.

[dantheman]

If something doesn't work, sometimes it's better to try something else. Especially when the only way to see if something is better is to try it.