I used o3 to profile myself from my saved Pocket links

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 Some were nearly accurate, some outdated, and plain "different".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.

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.

When moving my links from Pocket to Wallabag I passed them through Claude for tagging. Worked very well

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 could also ask the llm questions about each user.

It's not perfect, sometimes the inference gets something wrong or the less precise embeddings gets picked up which creates hallucinations or just nonsense, but it works somewhat!

I would love to improve on this or hear if anyone else has done something similar

Perhaps they're farming accounts? As in, the owner creates a whole bunch of accounts and has them build up a generic history. Then when the owner "deploys" some of them to pump up a specific issue. I don't know why they remove the posts, but perhaps it's a way of "recycling" an account by cleaning up the dirty work it did and throwing it back into the pool of available accounts?

Come to think of it, I bet the original creator is selling these accounts to someone else who is weaponizing them. Or the creator is renting them: build up a supply, rent them out for a purpose, then scrub them and recycle. Work From Home! Make Money Fast! This is one part of why the internet has gone to hell.

I don't have an explanation for why they'd delete the accounts.