What's your Pocket replacement? Wallabag, Hoarder or something else?
I used o3 to profile myself from my saved Pocket links
141–150 of 217 posts
Re: I used o3 to profile myself from my saved Pocket links
#142Thanks for the reminder that Pocket sunset is tomorrow. I did a quick analysis of my data as well via Claude Code: https://blog.kelvin.ma/posts/an-ode-to-pocket-analysis-of-ex...
Re: I used o3 to profile myself from my saved Pocket links
#143What's your Pocket replacement? Wallabag, Hoarder or something else?
reading an article if it's interesting and moving on if it's not :~^)
seriously though, i have struggled with tab/bookmark hoarding, it's a huge relief when you recognize it for what it is and quit. IME the bigger/dustier the backlog gets the more vague psychological guilt accumulates, a weight which isn't truly recognized until it's gone.
Re: I used o3 to profile myself from my saved Pocket links
#144Tell me what you read and I tell you who you are. Even though it might be surprising in which detail the model might give a feedback, it‘s not so hard to do this as a human, or is it?
From my perspective the most interesting thing might be the blind spots or unexpected results. The unknown knows which brings new aha effects
Re: I used o3 to profile myself from my saved Pocket links
#145Nice.
PS: is your blog self-hosted ? what's the stack here ?
Re: I used o3 to profile myself from my saved Pocket links
#146If 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…
It seems more reasonable to assume Google's been doing that since before Gmail launched.
Re: I used o3 to profile myself from my saved Pocket links
#147Tell me what you read and I tell you who you are. Even though it might be surprising in which detail the model might give a feedback, it‘s not so hard to do this as a human, or is it? From my perspective the most interesting thing might be the blind spots or unexpected results. The unknown knows which brings new aha effects
It's not hard to do this as a human, at least if that human is trained in gathering and transforming written information.
What makes a huge difference here is the ease and speed. I recently did a similar analysis of my HN posts. I have hundreds of posts, and it took like 30 seconds with high quality results. Achieving this quality level would have taken me hours, and I have some relevant experience.
This certainly opens up some new possibilities - good ones like self-understanding, potentially ambiguous ones in areas such as HR, and clearly dystopian ones ...
Re: I used o3 to profile myself from my saved Pocket links
#148Interesting article. Bizarrely it makes me wish I’d used Pocket more! Tangentially, with LLMs I’m getting very tired with the standard patter one sees in their responses. You’ll recognize the general format of chatty output:
Platitude! Here’s a bunch of words that a normal human being would say followed by the main thrust of the response that two plus two is four. Here are some more words that plausibly sound human!
I realize that this is of course how it all actually works underneath — LLMs have to waffle their way to the point because of the nature of their training — but is there any hope to being able to post-process out the fluff? I want to distill down to an actual answer inside the inference engine itself, without having to use more language-corpus machinery to do so.
It’s like the age old problem of internet recipes. You want this:
500g wheat flour
280ml water
10g salt
10g yeast
It was at the age of five, sitting
on my grandmother’s lap in the
cool autumn sun on West Virginia
that I first tasted the perfect loaf…Re: I used o3 to profile myself from my saved Pocket links
#149The 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
For many years I've used Pocket to give myself permission to get back to work.
Me too! I kind of wish I didn't know it was shutting down, and they just replaced the button with something that saves it to /dev/null without ever telling me.
Re: I used o3 to profile myself from my saved Pocket links
#150Interesting article. Bizarrely it makes me wish I’d used Pocket more! Tangentially, with LLMs I’m getting very tired with the standard patter one sees in their responses. You’ll recognize the general format of chatty output: Platitude! Here’s a bunch of words that a normal human being would say followed by the main thrust of the response that two plus two is four. Here are some more words that plausibly sound human!…
[dead]