News for hackers. Stuff that matters.

andrearitossa

Show HN: Recursive Human Intelligence: Actionable feedback from your LLM chats

https://github.com/andrearitossa/recursive-human-intelligence

Before Recursive Super Intelligence.. a lot of alpha can be squeezed by recursively improve humans.. Dont you think? That's the idea of Recursive Human Intelligence.Practically: it is a desktop that reads Claude Code, Codex, Pi chats, groups them into patterns and gives you specific feedback: touching habits that cost you time.It is bring-your-own LLM; in terms of data privacy it is operating...

( Read More... | no comments | on HN )
Re:Show HN: A guided 3D Leonardo da Vinci museum, built in code on Wednesday October 14, 2026 @01:48PM (#50091847)
I love it! Would be great to double down on the experience, I'd add immersive experiences: audio / visuals to guide the discovery / interactiveness
Connecting the dots from the ideas of his book "How Countries Go Broke: The Big Cycle" to today's macro and financial situation.

What's your take?

I had the same problem with "Deep Seek" classified in "web search" :>

I'd list it as limitation of embedding models pipelines. Fetching the link would drastically help, but I wont for now.

Ideas on solving the issue?

Any way you know I could contact the yc team to give them a quick heads up?
then you'd love the tool! You can follow your favourite topics
Check out the trends over time!
Good input: I just deployed a treemap of the topic post count over time.

How does it look? :>

Thanks :>
Yep! I deployed some hours ago a daily cronjob to keep up to date.
Then all your feedback for the app is greatly welcome!

Is there a particular language or piece of content you'd try searching for?

Great to hear :>

Good luck with your project!

I think it makes sense. I love the system to select comments of youtube and instagram (for different reasons). From a consumer perspective it seems that on yt time matters while for instagram personalization matters a lot.

Here personalization might be the most straightforward way to do this but it destroyes the beauty (for my little experience) of HN.. To have something based on where you're reading would be a crazy cool add on: comments of the text while you read through and final discussion comments.

What do you think?

The formular righ now for selecting in "the conversation now" is:

(points-1)× e^{-age in days / decay}

I am testing right now with decay: it was 14, I am wondering between 7 and 3.

Do you have suggestions on a different way to do it? Comments?

It is a map :> try again
Hi, great feedback!

I took the suggestions: now the connections are first page; cut pagination.

Because 5 of the first 8 topics are AI-related then these topics gets displayed on top when ordering per activity, it might look different in a couple of years :> for sure I could make a graph topic popularity by time and see the major tech trends by time, non trivial would be to compare it against the YC call for startups.

Giving this to YC would be super cool for me! Any suggestion on how to give this to them?

Re:Ask HN: Who wants to be hired? (June 2026) on Monday June 01, 2026 @03:17PM (#48361334)

  Location: Stockholm, SWE
  Remote: Yes
  Willing to relocate: Yes (for the right opportunity)
  Technologies: I am a new grad in System-Control and Robotics, experience in software engineering (backend and agentic AI), research in machine learning models for robotics manipulation and reinforcement learning for combinatorial optimization.
  Résumé/CV: https://www.linkedin.com/in/andrea-ritossa/
  Email: [email protected]