←back to thread

523 points noperator | 1 comments | | HN request time: 0.212s | source
Show context
nsypteras ◴[] No.44490417[source]
A while back I made a little script (for fun/curiosity) that would do this for HN profiles. It’d use their submission and comment history to infer a profile including similar stuff like location, political leaning, career, age, sex, etc. Main motivation was seeing some surprising takes in various comment threads and being curious about where it might have came from. Obviously no idea how accurate the profiles were, but it was similarly an interesting experiment in the ability of LLMs to do this sort of thing.
replies(3): >>44490446 #>>44491764 #>>44495141 #
morkalork ◴[] No.44490446[source]
Someone recently did this to predict what would hit the HN front page based on article content + profiles of users.
replies(2): >>44490525 #>>44496681 #
nsypteras ◴[] No.44490525[source]
That's pretty cool! Now I can imagine a tool that gives you a prediction before you even post and then offers suggestions for how to increase performance...
replies(1): >>44493032 #
tencentshill ◴[] No.44493032[source]
And now we see how easy it is to astroturf any given post, and that's without any budget.
replies(1): >>44493225 #
1. morkalork ◴[] No.44493225[source]
Gotta hand it to SamA for not only selling the problem but also trying to cash out on the solution (verified human via creepy orb eyeball blockchain thingy)