atulvi

I've been wanting something like this! but how does it stick?

Simply enter a topic you're interested in, and Wikidive will explore Wikipedia to find TWO related topics that an AI model thinks are interesting. You can then choose to dive deeper into one of these topics. Each "dive" presents you with related topics that you can explore further, creating an engaging journey of discovery.

EDIT: How it works:

It asks an llm this prompt: "I was going in this rabbit hole of wikipedia articles: #{chain} \n I have now found these topics:\n\n#{related_topics}\n\n Select the 2 most mind blowing topics from the list and that I'd enjoy given my rabbit hole. Ensure two topics are not the same."

and pics two articles that it returns. This is slightly better than random.(related article names are obtained from wikipedia API).

Wikidive is an AI-driven exploration tool designed to help you discover interesting topics on Wikipedia.

Simply enter a topic you're interested in, and Wikidive will explore Wikipedia to find TWO related topics that an AI model thinks are interesting. You can then choose to dive deeper into one of these topics. Each "dive" presents you with related topics that you can explore further, creating an engaging journey of discovery.

EDIT: How it works:

It asks an llm this prompt: "I was going in this rabbit hole of wikipedia articles: #{chain} \n I have now found these topics:\n\n#{related_topics}\n\n Select the 2 most mind blowing topics from the list and that I'd enjoy given my rabbit hole. Ensure two topics are not the same."

and pics two articles that it returns. This is slightly better than random.(related article names are obtained from wikipedia API).

There are several offensively titled events. No moderation whatsoever. This is likely 100% vibe coded in a day.

Switched to Linux for gaming. Getting more FPS on Linux too.

can this be done on real hardware with a modified controller?

What timing. I just got Schuam's Trigonometry to practice over the weekend and start a pure mathematics journey today and I see this article.

hugged to death

Made with phoenix liveview

This is cool as hell.

Low quality AI comment

OK, developer here. Here is how it works. It connects to groq and asks this

"I was going in this rabbit hole of wikipedia articles: #{chain} \n I have now found these topics:\n\n#{related_topics}\n\n Select the 2 most mind blowing topics from the list and that I'd enjoy given my rabbit hole. Ensure two topics are not the same."

and pics two articles that it returns. This is slightly better than random.(related article names are obtained from wikipedia API).

Right now, I'm maxed on daily Groq usage and the app falls back to pure random choice.

Why two articles? I was kind of going for a hot or not style system.

Anyway, it was a fun experiment. Learned lots.

OK, developer here. Here is how it works. It connects to groq and asks this

"I was going in this rabbit hole of wikipedia articles: #{chain} \n I have now found these topics:\n\n#{related_topics}\n\n Select the 2 most mind blowing topics from the list and that I'd enjoy given my rabbit hole. Ensure two topics are not the same."

and pics two articles that it returns. This is slightly better than random.(related article names are obtained from wikipedia API).

Right now, I'm maxed on daily Groq usage and the app falls back to pure random choice.

Why two articles? I was kind of going for a hot or not style system.

Anyway, it was a fun experiment. Learned lots.

I built this to recreate those late-night Wikipedia rabbitholes. It uses AI to find two fascinating interesting topics related to a topic you choose and then lets you dive deeper.

OK, this is it. The perfect firefox fork. The last thing I need is the ability to self host a ff sync server so my bookmarks are synced with my phone.

> weather station that reports temp/humidity/lignthing strikes/rain amount/wind speed+direction, and lux

Do you get this information from radio waves? would love to know more about your setup.