Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I used o3 to profile myself from my saved Pocket links

noperator.dev

Post reply on HN
Print view View original

101–110 of 217 posts

Re: I used o3 to profile myself from my saved Pocket links

#101

Post by AJ007 »

Alifatisk wrote: post #78

I did something similar, but for groupchats. You had to export a groupchat conversation into text and send it to the program. The program would then use a local llm to profile each user in the groupchat based on what they said. Like, it built knowledge of what every user in the groupchat and noted their thought on different things or what their opinions were on something or just basic knowledge of how they are. You c…

There are other good use cases here like documenting recurring bugs or problems in software/projects.

This is a good illustration of why e2e encryption is more important than its ever been. What were innocuous and boring conversations are now very valuable when combined with phishing and voice cloning.

OpenAI is going to use all of your ChatGPT history to target ads to you, and probably will have to choice to pay for everything. Meta is trying really hard too, and already is applying generative AI extensive for advertiser's creative production.

Ultra targeted advertising where the message is crafted to perfectly fit the viewer mean devices running operating systems incapable of 100% blocking ads should be considered malware. Hopefully local LLMs will be able to do a good job with that.

Re: I used o3 to profile myself from my saved Pocket links

#102

Post by cgriswald »

asveikau wrote: post #61

As someone with a family background of more left leaning Catholics (which I think are more common in the US northeast), it's interesting that it decided that you are conservative based on Catholicism.

To be fair, it actually said:

> Fiscally conservative / civil-libertarian with traditionalist social leaning

And justified it with:

> Bogleheads & MMM frugality + Catholic/First Things pieces, EFF privacy, skepticism of Big Tech censorship

First Things in its current incarnation is all about religious social conservatism. If someone is Catholic and reads First Things articles, "conservative" is a pretty safe bet.

However, I think profiling people based on what they read might be a mistake in general. I often read things I don't agree with and often seek out things I don't agree with both because I sometimes change my mind and because if I don't change my mind I want to at least know what the arguments actually are. I do wonder, though, if I tended to save such things to pocket.

Re: I used o3 to profile myself from my saved Pocket links

#103

Post by GMoromisato »

If you take the 13 seconds of processing time and multiply by 350 million (the rough population of the US), you get:

~144 years of GPU time.

Obviously, any AI provider can parallelize this and complete it in weeks/days, but it does highlight (for me at least) that LLMs are going to increase the power of large companies. I don't think a startup will be able to afford large-scale profiling systems.

For example, imagine Google creating a profile for every GMail account. It would end up with an invaluable dataset that cannot be easily reproduced by a competitor, even if they had all the data.

[But, of course, feel free to correct my math and assumptions.]

Re: I used o3 to profile myself from my saved Pocket links

#104

Post by sandspar »

elcapitan wrote: post #90

The main thing I learned from my pocket export is that 99% of the articles were "unread". Not sure if it would make sense to extrapolate something about myself other than obsessive link hording from this. :D

Perhaps comparing your read/unread might tell something about your revealed vs stated preferences. I assume that the typical person's unread pile is mostly aspirational. I'm sure that there's lots of data on this - for example Amazon's recommendation graph may weigh our Wishlist items differently than our Purchased items.

Re: I used o3 to profile myself from my saved Pocket links

#107

Post by elcapitan »

sandspar wrote: post #104
elcapitan wrote: post #90

The main thing I learned from my pocket export is that 99% of the articles were "unread". Not sure if it would make sense to extrapolate something about myself other than obsessive link hording from this. :D

Perhaps comparing your read/unread might tell something about your revealed vs stated preferences. I assume that the typical person's unread pile is mostly aspirational. I'm sure that there's lots of data on this - for example Amazon's recommendation graph may weigh our Wishlist items differently than our Purchased items.

I'm sure if you look long enough, you can find any pattern you want, and the opposite ;)

Re: I used o3 to profile myself from my saved Pocket links

#108

Post by kixiQu »

cgriswald wrote: post #102
asveikau wrote: post #61

As someone with a family background of more left leaning Catholics (which I think are more common in the US northeast), it's interesting that it decided that you are conservative based on Catholicism.

To be fair, it actually said: > Fiscally conservative / civil-libertarian with traditionalist social leaning And justified it with: > Bogleheads & MMM frugality + Catholic/First Things pieces, EFF privacy, skepticism of Big Tech censorship First Things in its current incarnation is all about religious social conservatism. If someone is Catholic and reads First Things articles, "conservative" is a pretty safe bet. How…

I have a hypothes.is account where a decent amount of my annotations are little rage nits against the thing I'm reading. You'd be able to infer a ton of correct information from me if you pulled the annotations as well as the URLs, but the URLs alone could mislead.

I've had to remind myself of this pattern with some folks whose bookmarks I follow, because they'd saved some atrocious stuff – but knowing their social media, I know they don't actually believe the theses.

Re: I used o3 to profile myself from my saved Pocket links

#109

Post by CGMthrowaway »

asveikau wrote: post #82
CGMthrowaway wrote: post #74

Earlier quoted context omitted.

I would say in aggregate, both Catholics and Protestants (whichever flavor) are more likely to be liberal in the northeast / west coast and more likely to be conservative in the midwest / south. Which tells you something about the average importance of religion in 2025.

I think it's older than 2025 and definitely has a piece of it that is specific to Catholics. I tend to think of northeastern American Catholicism from the lens of immigration. The big waves of Italians, Irish, Eastern Europeans, etc. The immigrant identity often led to left leaning economics and the parts of Christianity which are about helping the poor get emphasized.

Idk how much experience you have with catholics outside of the northeast. I have a fair amount with all of the regions I mentioned (northeast, south, midwest, west coast). You cannot really find any American Catholic parish that is not dominated by at least one of Italians, Irish, Eastern Europeans or Hispanics. The catholic church in the US is mostly "immigrants," that is, people whose ancestors were not in the US prior to ~1850

Re: I used o3 to profile myself from my saved Pocket links

#110

Post by cluckindan »

hubraumhugo wrote: post #23

I built a similar tool that profiles/roasts your HN account: https://hn-wrapped.kadoa.com/ It’s funny and occasionally scary Edit: be aware, usernames are case sensitive

It would be much funnier and/or insightful if it sampled more than the first page of user comments.

Still, spot on:

Predictions

Personal Projects

After a deep dive into archaic data storage, you'll finally release 'Magnetic Tape Master 3000' – a web-based app that simulates data retrieval from a reel-to-reel, complete with authentic 'whirring' sound effects. It'll be a niche hit with historical computing enthusiasts and anyone who misses the good old days of physical media.

Post reply on HN