[nsypteras]

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.

[morkalork]

Someone recently did this to predict what would hit the HN front page based on article content + profiles of users.

[nsypteras]

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...

[swyx]

link please? if you can find it

[nozzlegear]

> Main motivation was seeing some surprising takes in various comment threads and being curious about where it might have came from.

It'd be interesting to run it on yourself, at least, to see how accurate it is.

[mywittyname]

I remember this. It was pretty accurate for myself, if a little saccharine (i.e., it said I was going to save the world, or some such).