Viewing profile — vitaelabitur

Hey everybody, sharing Ami on HN today. Ami is an open source, local-first agent harness that acts as your shadow worker and copilot chat. It ships with a graph memory. Here's what…

thanks a lot, much appreciated

Yeah, pretty accurate description of how depression looks. I'm reminded of Lars von Trier's Melancholia. I don't recommend it to anyone but it's the best, most visceral portrayal o…

Shameless plug for my structured LLM outputs handbook which is written in a similar spirit: https://nanonets.com/cookbooks/structured-llm-outputs/

Thanks for sharing, appreciate it. Would you say it is convenient to use it for writing, say, 500 words at a go?

I want an e-ink display to read books and write my random musings, journal entries, notes. I'll be able to make good use of it, so I am willing to pay for quality. Audiobooks suppo…

> And really, really boring and slow a lot of the time If you only watch the story-driven scenes in Lawrence of Arabia, and skip the prolonged shots of the desert, you would miss o…

The word you are looking for, if you are looking for one, is declinism.

We traded books for films, and now films for short videos, always moving towards what is easier to enjoy. Quite a while ago, books became a taste that needs to be patiently acquire…

This is my all-time favorite mathematics book. It approaches calculus fundamentals through a series of fictional conversations between a teacher and a student. It is easy to read, …

You are absolutely right — Let me know if you want to read my personal anecdote on "Dead Internet Theory"... Yeah, I especially hate how paranoid everyone is (but rightly so). I am…

There's no advantage wrt output quality, but it can be more economical in some high-error regimes, with less LLM calls used in resampling (max 2 for most errors).

We used Docusaurus.

One of the authors here. I've read the paper. Brilliant work, especially the slicing implementation for denser token masks.