Recalling Simon Willison’s recent geoguessing challenge for o3, I considered, “What might o3 be able to tell me about myself, simply based on a list of URLs I’ve chosen to save?”
I do this to determine if a person I'm talking to online is potentially a troll. I copy a big chunk of their comment and post history into an LLM and ask for a profile.
The last few years, I've noticed an uptick in "concern trolls" that pretend to support a group or cause while subtly working to undermine it.
LLMs can't make the ultimate judgement call very well, but they can quickly summarize enough information for me to.
It's nearly impossible to determine whether or not someone is expressing a concern in good faith, so what ends up happening is people getting silenced for diverting even slightly from the dominant narrative because nobody is ever given the benefit of the doubt.
One thing I've seen happen with some of these accounts is they remove a lot of their posts after some period of time.
So they make somewhat consistent 'generic' posts that do not get remove, but do not really convey any signal on their actual views.
Then in their last 24-48 hours there are more political style posts/concern posts that only stick around while the article/post is getting views. Then replies disappear like they've never happened so you can't tell it's an account that exists wholly to manipulate others that has been doing so for months.
Then quite often after a month or two the accounts disappear totally.
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.
Why the clickbait title? Yes, it's technically correct, but it obviously implies (as written) that o3 used those links "behind your back" and altered the replies.
Another option that's just as correct and doesn't mislead: "Profiling myself from my Pocket links with o3"
Note: title when reviewed is "o3 used my saved Pocket links to profile me"
I've been thinking about the possibities of using an LLM to sort through all my tabs; I'm one of those dreadful hoarders that has been living with the ":D" count on my phone for too long. Usually I purge them periodically but I haven't had the motivation to do do so in a long time. I just need an easy way to dump them to a csv or something like OP has from pocket.
I did this recently with my unsorted bookmarks! It was the first time I used parallel API calls. Ten gpt-4-nano threads classifying batches of ten bookmarks ripped through 10,000 bookmarks in a few minutes.
Is anyone using "AI chatbots" considering they are handing a detailed profile of their interests, problems, emotional struggles, vulnerabilities to advertisers? The machine has "the other end", you know, and we're feeding already enourmously powerful people with more power.
After reading this I realized I also have an archive of my pocket account (4200 items), so tried the same prompt with o3, gemini 2.5 pro, and opus 4:
- chatgpt UI didn't allow me to submit the input, saying it's too large. Although it was around 80k tokens, less than o3's 200k context size.
- gemini 2.5 pro: worked fine for personality and interest related parts of the profile, but it failed the age range, job role, location, parental status with incorrect perdictions.
- opus 4: nailed it and did a more impressive job, accurately predicted my base city (amsterdam), age range, relationship status, but didn't include anything about if I'm a parent or not.
Both gemini and opus failed in predicting my role, probably understandably. Although I'm a data scientist, I read a lot about software engineering practices because I like writing software and since I don't have the opportunity at work to do this kind of work, I code for personal projects, so I need to learn a lot about system design, etc. Both models thought I'm a software engineer.
Overall it was a nice experiment. Something I noticed is both models mentioned photography as my main hobby, but if they had access to my youtube watch history, they'd confidently say it's tennis. For topics and interests that we usually watch videos rather than reading articles about, would be interesting to combine the youtube watch history with this pocket archive data (although it would be challenging to get that data).
You need to use an iterative refinement pyramid of prompts. Use a cheap model to condense the majority of the raw data in chunks, then increasingly stronger and more expensive models over increasingly larger sets of those chunks until you are able to reach the level of summarization you desire.
I think a reasoning/thinking-heavy model would do better at piecing together the various data points than an agentic model. Would be interested to see how o3 does with the context summarized.
You should be able to use Google Takeout to get all of your YouTube data, including your watch history.
This article is a nice example of someone using it:
> When I downloaded all my YouTube data, I’ve noticed an interesting file included. That file was named watch-history and it contained a list of all the videos I’ve ever watched.
re o3: you can zip the file, upload it, and it will use python and grep and the shell to inspect it. I have yet to try using it with a sqlite db, but that's how i do things locally with agents.
Another thing one could do with a flat list of hundreds of saved links (if it's being used for "read it later", let's be honest: a dumping ground) is to have AI/NLP classify them all, to make it easy to then delete the stuff you're no longer interested in.
I recently migrated to Linkwarden [0] from Pocket, and have been fairly happy with the decision. I haven't tried Wallabag, which is mentioned in the article.
Linkwarden is open source and self-hostable.
I wrote a python package [1] to ease the migration of Pocket exports to Linkwarden.
i've mentioned in this in a few Show HNs, been working on an AI bookmarking and notes app called Eyeball: https://eyeball.wtf/
It integrates a minimalist feed of your links with the ability to talk to your bookmarks and notes with AI. We're adding a weekly wrapped of your links next week like this profile next week.
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.
I’ve been really interested in stuff like this recently. Not just Pocket saves but also meta analysis of ChatGPT/Gemini/Claude chat history.
I’ve been using an ultra-personalized RSS summary script and what I’ve discovered is that the RSS feeds that have the most items that are actually relevant to me are very different from what I actually read casually.
What I’m going to try next is to develop a generative “world model” of things that fit in my interests/relevance. And I can update/research different parts of that world model at different timescales. So “news” to me is actually a change diff of that world model from the news. And it would allow me to always have a local/offline version of my current world model, which should be useful for using local models for filtering/sorting things like my inbox/calendar/messages/tweets/etc!
I did the same exercise a while back with 4o but to do it based on the questions I have asked it so far. Some were nearly accurate, some outdated, and plain "different". It felt good, but ultimately realized its system prompt is designed to make me feel good.
---
Here’s the high-level picture I’ve built of you from our chats:
- You’re a senior/lead developer in India, aiming to step up into a staff-developer or solution-architect role.
- You have a healthy dose of self-doubt (especially around soft skills), and you’ve been deliberately working on both your technical breadth (authentication in ASP .NET, Linux, C++/Qt, distributed systems, data visualization, AI foundations) and your communication/architectural toolkit (presentations, executive summaries, third-party evaluations).
- You’re a Linux enthusiast, intrigued by open source, server-side flows, rate limiting, authentication/authorization, and you love building small, real-world exercises to cement concepts.
- You prize clarity, depth, minimalism, and originality—you dislike fluff or corporate buzzwords.
- You have a hacker-philosopher energy: deeply curious, systems-thinking-oriented, with a poetic streak.
- You’re comfortable with both structured roadmaps and creative, lateral thinking, and you toggle seamlessly between “hard” dev topics and more reflective, meta-tech discussions.
- Right now, you’re honing in on personal branding—finding a domain and a blog identity that encapsulates your blend of tech rigor and thoughtful subtlety.
77 comments
[ 2.6 ms ] story [ 74.7 ms ] threadThe last few years, I've noticed an uptick in "concern trolls" that pretend to support a group or cause while subtly working to undermine it.
LLMs can't make the ultimate judgement call very well, but they can quickly summarize enough information for me to.
So they make somewhat consistent 'generic' posts that do not get remove, but do not really convey any signal on their actual views.
Then in their last 24-48 hours there are more political style posts/concern posts that only stick around while the article/post is getting views. Then replies disappear like they've never happened so you can't tell it's an account that exists wholly to manipulate others that has been doing so for months.
Then quite often after a month or two the accounts disappear totally.
It'd be interesting to run it on yourself, at least, to see how accurate it is.
"The need to be observed and understood was once satisfied by God. Now we can implement the same functionality with data-mining algorithms."
Another option that's just as correct and doesn't mislead: "Profiling myself from my Pocket links with o3"
Note: title when reviewed is "o3 used my saved Pocket links to profile me"
- chatgpt UI didn't allow me to submit the input, saying it's too large. Although it was around 80k tokens, less than o3's 200k context size.
- gemini 2.5 pro: worked fine for personality and interest related parts of the profile, but it failed the age range, job role, location, parental status with incorrect perdictions.
- opus 4: nailed it and did a more impressive job, accurately predicted my base city (amsterdam), age range, relationship status, but didn't include anything about if I'm a parent or not.
Both gemini and opus failed in predicting my role, probably understandably. Although I'm a data scientist, I read a lot about software engineering practices because I like writing software and since I don't have the opportunity at work to do this kind of work, I code for personal projects, so I need to learn a lot about system design, etc. Both models thought I'm a software engineer.
Overall it was a nice experiment. Something I noticed is both models mentioned photography as my main hobby, but if they had access to my youtube watch history, they'd confidently say it's tennis. For topics and interests that we usually watch videos rather than reading articles about, would be interesting to combine the youtube watch history with this pocket archive data (although it would be challenging to get that data).
What you do at work today doesn't mean you can't switch to a related ladder.
This article is a nice example of someone using it:
> When I downloaded all my YouTube data, I’ve noticed an interesting file included. That file was named watch-history and it contained a list of all the videos I’ve ever watched.
https://blog.viktomas.com/posts/youtube-usage/
Of course as an European it's a legal obligation for companies to give you access, but I think Google Takeout works worldwide?
You probably still are, even if that's not your career path :)
https://takeout.google.com/settings/takeout/custom/youtube?p...
And then a combination of pup and jq to parse the video titles from the HTML file:
It’s funny and occasionally scary
Edit: be aware, usernames are case sensitive
Seems to be a fairly common issue.
Linkwarden is open source and self-hostable.
I wrote a python package [1] to ease the migration of Pocket exports to Linkwarden.
[0] https://linkwarden.app/
[1] https://github.com/fmhall/pocket2linkwarden
It integrates a minimalist feed of your links with the ability to talk to your bookmarks and notes with AI. We're adding a weekly wrapped of your links next week like this profile next week.
I’ve been using an ultra-personalized RSS summary script and what I’ve discovered is that the RSS feeds that have the most items that are actually relevant to me are very different from what I actually read casually.
What I’m going to try next is to develop a generative “world model” of things that fit in my interests/relevance. And I can update/research different parts of that world model at different timescales. So “news” to me is actually a change diff of that world model from the news. And it would allow me to always have a local/offline version of my current world model, which should be useful for using local models for filtering/sorting things like my inbox/calendar/messages/tweets/etc!
---
Here’s the high-level picture I’ve built of you from our chats:
- You’re a senior/lead developer in India, aiming to step up into a staff-developer or solution-architect role.
- You have a healthy dose of self-doubt (especially around soft skills), and you’ve been deliberately working on both your technical breadth (authentication in ASP .NET, Linux, C++/Qt, distributed systems, data visualization, AI foundations) and your communication/architectural toolkit (presentations, executive summaries, third-party evaluations).
- You’re a Linux enthusiast, intrigued by open source, server-side flows, rate limiting, authentication/authorization, and you love building small, real-world exercises to cement concepts.
- You prize clarity, depth, minimalism, and originality—you dislike fluff or corporate buzzwords.
- You have a hacker-philosopher energy: deeply curious, systems-thinking-oriented, with a poetic streak.
- You’re comfortable with both structured roadmaps and creative, lateral thinking, and you toggle seamlessly between “hard” dev topics and more reflective, meta-tech discussions.
- Right now, you’re honing in on personal branding—finding a domain and a blog identity that encapsulates your blend of tech rigor and thoughtful subtlety.